Signal Nodus SEC Filings

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and openWorldHint=true, so the description does not need to re-state safety. It adds valuable context: the ordering ('newest first'), the window parameter, and the cost per call ($0.05). This goes beyond annotations and covers practical constraints, though it doesn't describe return format or pagination, keeping it at a 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first states the core function with specifics (filings, company, window, ordering), and the second provides the activist context and cost. Every word adds value, with no fluff or redundancy. It is front-loaded and highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does not explain the exact structure of returned filings, but it does convey the nature of the data (13D/13G filings) and the ordering. Given the tool's simplicity (3 params, clear purpose) and the strong annotations, the description is largely sufficient. A minor gap is the lack of mention of what fields are in the response, but it does not detract significantly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema descriptions for all three parameters are complete (100% coverage), so the description does not need to repeat them. It does add a little context by mentioning 'over a window' which aligns with the 'days' parameter, but no extra meaning beyond the schema is provided. The baseline of 3 is appropriate given the schema already carries the parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves Schedule 13D and 13G beneficial-ownership filings for a specific company over a time window, sorted newest first. It explicitly names the regulatory filings (13D/13G) and the activist-position context, which distinguishes it from generic filing tools like latest_filings or recent_filings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: it is the first public signal of an activist position, implying use when seeking activist stake information. It mentions the cost per call, which is useful for decision-making. However, it does not explicitly state when NOT to use it or mention alternatives (e.g., using recent_filings for broader filing needs), so it falls slightly short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, but the description adds valuable behavioral context beyond these: it is 'Experimental (may change or be withdrawn),' it 'costs $0.05 per call,' and it discloses 'the disclosed record only, no forecast.' These details warn the agent about volatility and cost, which are not captured in annotations. No contradiction with annotations; it complements them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately long and front-loads an 'Experimental' parenthetical that, while important, adds verbosity before the core purpose. The structure is clear (purpose, matching, cost) but could be tightened by moving the experimental note to a single clause. Every sentence has a purpose, but the opening is heavier than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only data retrieval tool with no output schema, the description thoroughly explains what is returned (longs, shorts, net, share of open interest, changes), the matching rule, limitations (no forecast, disclosed record only), and the cost. It also flags experimental status. The agent has enough to call it correctly without missing critical expectations, though pagination or response format are not detailed—minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters; the schema already explains 'weeks' with max/default and 'market' as a contract name fragment with examples. The description reiterates the matching-by-fragment behavior and gives the same examples, adding no novel semantic information. Since the schema handles parameter meaning well, a baseline score of 3 is appropriate; the description does not compensate for any gaps because none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool provides Weekly Commitments of Traders positioning, listing the exact metrics (non-commercial/commercial longs, shorts, net, share of open interest, week-over-week changes). It clarifies matching by contract name fragment, which distinguishes it from sibling tools like crop_data or energy_data that cover other data domains. The verb 'provides' and resource ('CFTC futures positioning') are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (when CFTC futures positioning data is needed) and even gives matching examples, but it does not explicitly mention alternatives or exclusions. It only notes it is 'outside the core SEC path,' which hints at scope but does not name sibling tools or state when not to use it. For an agent, the domain is clear, but guidance on selection among siblings is absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly and openWorld annotations, the description discloses the per-call cost and payment method (credit key or machine payment), which are crucial behavioral details not captured elsewhere. It also notes the revenue concept discrepancy, adding transparency about potential empty results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with a clear main sentence, a useful note, and a cost/payment sentence. It avoids unnecessary verbosity and is well-structured, though the revenue note could be seen as slightly tangential.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core functionality, cost, and a data nuance, but lacks specifics such as the number of periods returned, handling of missing data, or output format. Since there is no output schema, these details would be valuable for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides full coverage for both parameters. The description adds context about 'as-reported' and 'recent periods' but does not elaborate on the semantics of the parameters themselves beyond the revenue tip, which is a specific example rather than general parameter guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it fetches an as-reported XBRL financial concept for a company across recent periods, which is a specific verb+resource. It distinguishes from siblings like verify_financial_claim or who_holds by focusing on raw XBRL data, though it doesn't explicitly contrast with alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a practical tip about revenue concept alternatives and mentions cost and payment requirements, implying when to use it. However, it does not explicitly state scenarios where other tools would be preferred, so it falls short of the highest level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly and openWorld annotations, the description discloses several important behaviors: it errors rather than returning a misleading 0% change, warns about later amendments, reports which filings were compared, can take tens of seconds, and costs $0.50 per call. This is rich, actionable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but efficient, front-loading the core purpose and then covering usage, failure modes, performance, and cost. A few extras like the evaluation link could be trimmed, but the structure is logical and every sentence carries useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even without an output schema, the description explains enough about the result format, fallback behavior, failure conditions, latency, and authentication requirement for an agent to call the tool correctly. Nothing critical for invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the role of accession parameters in controlling which filings are compared, and by clarifying that omitted accessions fall back to the two most recent filings. This goes beyond the schema's field-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('diff') and resource ('a 10-K risk-factor or MD&A section'), and clearly states the output: added and removed passages plus a change ratio. This distinguishes it from sibling tools like filing_section or edgar_search, which fetch or search rather than compare.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete guidance on how to pin exact filings using accession numbers and what happens when they are omitted, including amendment warnings. It does not explicitly name alternative sibling tools or state when not to use this tool, but the intended context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint and openWorldHint, but the description adds valuable behavioral context beyond that: it notes a $0.05 per-call cost, that values are as published including NASS suppression markers, and that the tool is experimental with potential changes or withdrawal. These are meaningful operational traits that help an agent budget and trust the data, going beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, front-loading the important 'Experimental' warning before the core purpose and cost. Every sentence adds value: the experimental status, the data source and types, the data fidelity note, and the cost. It's slightly long but not bloated, and the key information is prioritized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a data retrieval tool with 5 parameters and no output schema, the description covers the data source, statistic types, geographic scope, and cost—good foundation. However, it does not describe the return format (e.g., JSON, CSV) or pagination behavior, which an agent would need to parse results. The mention of suppression markers hints at data handling but not the response structure. This is a moderate gap given no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all five parameters with appropriate details. The description adds little new per-parameter meaning; it reinforces that statistics cover yields, production, etc., which mirrors the 'statistic' enum. Since the schema carries the semantic weight, a baseline of 3 is appropriate—the description does not compensate for any gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides official USDA NASS estimates, listing the specific statistic types (yields, production, area, stocks, prices) and geographic scope (national or by state). This is a specific resource and purpose, distinguishing it from siblings like energy_data or fx_rate. It could be even more explicit about the tool's name, but the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus alternatives. It only warns that it's experimental and may change, which is a caveat but not usage direction. There is no mention of when to prefer crop_data over other data tools like energy_data or trade_flows, nor any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral context: it is experimental, not covered by the accuracy eval, may change or be withdrawn, and costs $0.01 per call. It also details the exact data points returned. This goes beyond the annotations to disclose stability, cost, and scope of behavior, though it does not describe failure modes or formatting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence. It front-loads the critical experimental warning, then lists the data points returned, and ends with the cost. There is no fluff or redundant wording. Every element earns its place, making it highly efficient for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a single required parameter and no output schema, yet the description enumerates exactly what will be returned (DNS records, SPF, registration details, etc.), giving the agent a clear expectation of the result. It also covers cost and stability. The only omission is discussion of error handling or edge cases (e.g., invalid domains), but given the openWorldHint, this is acceptable. The description is largely complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes the only parameter 'domain' with the requirement 'Bare hostname, e.g. example.com.' The description adds no additional parameter information beyond what the schema provides. With 100% schema coverage, the baseline of 3 is appropriate; the description does not need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving DNS records, SPF presence, registration date/age, registrar, expiry, and RDAP status for a single hostname. The verb is implied (get/report), the resource is explicit (domain information), and the scope is precisely defined. None of the sibling tools overlap with this domain-specific query, so it is easily distinguishable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context that this tool is 'experimental' and 'outside the core SEC path', implying it is not for standard SEC-related queries but for domain information. However, it does not explicitly state when to use it over alternatives or name any alternative tools. The guidance is implied rather than explicit, so while it informs the agent of its niche, it lacks direct usage instructions or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=true and openWorldHint=true, but the description adds valuable behavioral context: the search is exact-phrase, covers all filings since 2001, and incurs a $0.01 per-call cost. It also states what data is returned. This goes beyond the annotations without contradicting them, providing useful operational details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the core purpose, then immediately states the returned data and cost. Every word adds value, with no fluff or redundancy. It efficiently communicates the tool's utility and integration with other tools.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (5 params, all well-documented in schema) and no output schema, the description adequately covers the return payload (company, form, date, accession number). It also notes the cost and downstream applicability, making it complete for an agent to decide on usage. No gaps that would hinder correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% description coverage for all parameters, so the description doesn't need to add much. It does hint that the 'q' parameter is an exact phrase (reinforced in description) and mentions limit defaults, but no additional semantics beyond the schema. Baseline 3 is appropriate given schema coverage is high.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs exact-phrase full-text search over all EDGAR filings since 2001 and lists the returned fields (company, form, date, accession number). It explicitly distinguishes from siblings like filing_section and compare_filings by positioning results as ready for those tools, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context on when to use it (searching for filings containing a specific phrase) and suggests downstream tools (filing_section, compare_filings). However, it lacks explicit exclusions (e.g., when not to use vs. latest_filings), so it's not fully explicit about alternatives, but the guidance is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint and openWorldHint. The description adds useful behavioral context: the experimental status, per-call cost, newest-period-first ordering, and the fact that data may change or be withdrawn. These go beyond annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, information-dense sentence packs all critical details: experimental flag, data source, series list, ordering, and cost. No filler or redundancy; every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers the three series and their units, it does not clarify how the 'region' parameter applies to fuel_price (the schema only links it to grid_demand). There is no output schema, so the return format is unspecified. These gaps could lead an agent to misuse the tool or misunderstand its response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter is described. The description adds meaningful units (cents per kWh, dollars per gallon) and clarifies what each series returns, enriching the agent's understanding beyond bare schema descriptions. However, the mapping of the 'region' parameter to fuel_price is left ambiguous, slightly reducing its value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it provides Official EIA energy figures across three distinct series (electricity_price, fuel_price, grid_demand), each with its own scope. This differentiates it from the many SEC/financial sibling tools, making its purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly flags the tool as experimental and outside the core SEC path, warning it may change or be withdrawn. It does not name alternatives, but no sibling overlaps functionally, so the context is sufficiently clear. Cost information adds practical guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint and openWorldHint annotations already covering safety, the description adds valuable context: experimental status (outside SEC eval, may change), cost ($0.01 per call), and data source (public RPC). These disclose operational traits beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with the experimental caveat front-loaded, followed by the core function and cost. It is efficient, with no redundant phrases, though the caveat is slightly lengthy. Structure is logical and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with 2 params and no output schema, the description covers essential operational context: experimental status, cost, data source, and the inclusion of block height in the response. It does not specify balance units (e.g., wei), which is a minor gap but acceptable given the simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both params described (chain and address). The description does not add new parameter semantics beyond the schema, so baseline 3 is appropriate. The mention of 'block height' describes output, not a parameter, and is a minor addition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: retrieving the native balance of any 0x address on Base or Ethereum, with block height, from public RPC. This distinguishes it from siblings like evm_gas (gas prices) and token_price (token balances) by focusing on native balance and chain specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: use this for native balance on Base/Ethereum, but it does not explicitly contrast with sibling tools (e.g., token_price for token balances) or state when not to use it. It provides context but lacks explicit routing to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnlyHint and openWorldHint, so the description's additional caveats are valuable. It discloses that the tool is experimental, may change or be withdrawn, costs $0.01 per call, and reports block height alongside the gas price. This goes beyond the annotations and gives the agent useful operational context about reliability and cost.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the most important caveat (experimental status) before stating the core purpose and cost. Every sentence carries essential information without redundancy, making it easy for an agent to process quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one optional parameter, no output schema), the description is fully sufficient. It covers the experimental nature, cost, what is returned (wei and gwei with block height), and the default behavior via schema. There is no missing information an agent would need to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully describes the only parameter (chain) with values 'base or ethereum' and a default of 'base', so schema coverage is 100%. The description adds no additional meaning to the parameter, such as format constraints or examples, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the current gas price in wei and gwei along with block height, identifying the specific resource and output. However, it does not explicitly mention that it serves Base or Ethereum chains (though this appears in the title), and it does not differentiate itself from the sibling tool gas_optimizer, which could cause confusion about which to use for gas-related queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. The experimental status and note about being outside the core SEC path are caveats, but they do not instruct the agent on selection criteria or when to prefer this tool over related ones like evm_balance or gas_optimizer. No exclusions or alternative routing is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds the experimental status, the $0.01 cost per call, and lists the specific data fields returned. This goes beyond annotations, though it doesn't mention potential failure modes or behavior under invalid hashes. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with the experimental note front-loaded, followed by the output fields and cost. No redundant words; every clause adds value. The structure is efficient and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description enumerates the return fields (status, gas used, effective gas price, log count) which suffices for basic usage. It also mentions cost and experimental nature. However, it omits details like response formats, error handling, or chain-specific behavior, which a richer description might include for an experimental tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides full descriptions for both parameters (tx: '0x-prefixed transaction hash', chain: 'base or ethereum. Default base.'). The description does not add further parameter-specific detail, relying on the schema's 100% coverage. It only restates 'transaction hash' in prose, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource: 'transaction hash', and the specific output: 'Status, gas used, effective gas price and log count'. It says the verb implicitly (returns/provides) which is appropriate. It distinguishes itself from sibling EVM tools (like evm_balance, evm_gas) by its output focus on receipts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when a transaction receipt is needed, mentioning 'for a transaction hash'. However, it does not explicitly contrast with alternatives (e.g., when to use evm_balance for balances) or provide conditions for when not to use it. The experimental caveat gives context but not routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint and openWorldHint, so the bar is lower. The description adds valuable behavioral details beyond annotations: the cost ($0.05 per call) and the distinction between eventDate (when it happened) and filedAt (when disclosed). It also mentions that item codes are decoded, which clarifies output content. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and efficiently packs in item code examples, date semantics, and pricing. Every sentence earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 params, no output schema), the description covers the essential aspects: what it does, key output fields (eventDate vs filedAt), item code filtering, and cost. It doesn't mention pagination, ordering, or output structure, but the schema and purpose are clear enough for an agent to infer typical usage. It is reasonably complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds a bit of extra context for the 'item' parameter by giving concrete examples of item codes (e.g., 5.02 for executive departures), which helps interpret the filter. However, it does not elaborate on other parameters beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: parsing a company's 8-K filings into material events with decoded item codes, providing examples (5.02, 4.02, etc.). It distinguishes itself from siblings like filing_section or latest_filings by focusing on parsed events rather than raw filings or sections. The verb 'parsed' and the resource '8-K filings' are specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining material events from 8-K filings, but it does not explicitly mention when to use this over alternatives like filing_section or recent_filings. It does provide cost information, which is relevant for usage decisions. However, no explicit when-not or alternative tool references are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and openWorldHint=true, so the description does not need to restate those. It adds substantial behavioral detail beyond annotations: failure behavior when the item heading is hidden, response fields (accessionNumber, filingDate, source URL, parserVersion), latency for large filings, cost per call, payment method, and a reference to a public accuracy evaluation. This is rich and directly helps the agent anticipate outcomes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph but slightly long. However, every sentence earns its place: purpose is front-loaded, followed by the value proposition, accession behavior, failure mode, response contents, accuracy, latency, cost, and payment. It is efficient given the amount of critical operational information, though it could be tightened by grouping related points.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and five parameters, the description covers all necessary information: input semantics (via parameter details), output structure (response fields), failure modes, operational characteristics (latency and cost), and authentication requirements (credit key or machine payment). Nothing an agent needs to call it correctly or interpret results is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds extra meaning for 'accession' by explaining the default behavior when omitted, and for 'item' by noting that omitting it lists available items. It also clarifies the function of 'max_chars' implicitly through the truncation context. These additions go beyond the schema descriptions without repeating them, adding agent-relevant nuance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('pull') and resource ('single numbered item out of a 10-K or 10-Q'), and names common items like 1A, 7, and 1. It clearly distinguishes from sibling tools like compare_filings or edgar_search by focusing on extraction of one section as clean text, with no ambiguity about scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context: explains why to use it ('saves you fetching a multi-megabyte HTML document'), and describes the difference between providing an accession number (pins exact filing) versus omitting it (gets most recent filing) with a warning about amendments. It also notes that omitting 'item' lists available items. However, it does not explicitly name sibling alternatives or state when not to use it, leaving some inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description supplements this by disclosing that the rate is a daily fix (not real-time), that it is experimental and may change/withdraw, and that each call costs $0.01. These add practical behavioral context beyond the annotations, such as cost and stability, which are not captured structurally.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence but contains several pieces of information packed in a structured way: an initial caveat, the core purpose, a note on frequency, and cost. It is not wordy, but the caveat at the beginning is slightly long and could be moved to the end for better front-loading of the purpose. Still, it is efficient and every clause adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (two optional parameters, no required fields, no nested objects) and the description covers purpose, cost, and the daily-fix nature. However, with no output schema, the description should indicate what the return value looks like. It says 'rates from one base currency to up to ten targets' but does not specify the structure (e.g., a map, list, or single value). This omission means an agent may not know how to parse the result, making it incomplete on output semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema describes each parameter, but the description adds meaningful semantics: it specifies 'up to ten targets' and mentions ISO 4217, which clarifies the allowed values and format beyond the schema's generic 'comma list'. It also implies that 'from' is a single base currency, which is implicit but reinforced.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (ECB reference rates), the action (provide rates), and the scope (one base to up to ten targets, ISO 4217). It also distinguishes from siblings by noting it is not a tradable quote, which differentiates it from potential market data tools. The verb 'provides' is implicit but clear from context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives context: it is a daily fix, not a tradable quote, and costs money, which hints at suitability for reference use rather than live trading. However, it does not explicitly state when to use this tool versus alternatives, nor does it name any sibling tools or exclude use cases. The caveat about being experimental and not covered by accuracy eval is more about trust than usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description correctly does not repeat that. It adds significant behavioral context: experimental status, exclusion from accuracy eval, potential to change or be withdrawn, the $0.05 per-call cost, and the limitation to network fee only. These go well beyond the structured fields and set accurate expectations for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that packs multiple important clauses (cost, chains, metric, exclusions, price, experimental caveat). Every clause carries useful information with no filler, though the density could be seen as slightly heavy. It is front-loaded with 'Experimental' to set expectations immediately, which is effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description is remarkably complete. It explains what is returned conceptually (USD costs per chain and identification of the cheapest), sets a clear boundary (network fee only), and flags all critical caveats (cost, experimental, not a quote). An agent has everything needed to decide whether and how to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: the only parameter 'chains' is fully described in the schema (comma list, allowed values, default). The tool description adds no additional parameter-level detail beyond that, so it meets the baseline of 3 but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb ('Compare live network fees'), the resource ('across Base, Arbitrum, and Ethereum'), and the metric ('USD cost of a standard native transfer'). It also explicitly names the output concept ('cheapest chain named'), which distinguishes it from a generic gas-price tool like evm_gas. The mention of 'not a route or swap quote' further disambiguates it from swap-related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides strong usage context: it is for comparing gas costs across chains, with a cost per call and experimental status. It explicitly states it is not a route or swap quote, which is a clear exclusion. However, it does not explicitly name alternatives (e.g., evm_gas for single-chain gas price) or give a 'when not to use' beyond that, so it earns a 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. Description adds useful behavioral context: experimental/unstable, cost per call, recipient name-text matching, and output ordering (largest first). No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise but packs key info: experimental status, cost, output fields, matching method. Front-loaded with the most important caveat. Not overly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Completeness is good for a simple tool with 3 params and no output schema. Includes cost, experimental nature, and return fields. Missing pagination or no-result behavior, but not critical given tool simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all parameters with descriptions, so baseline is 3. Description adds no parameter-specific details beyond schema, though it clarifies matching is by name text for the company param, a small addition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it returns federal prime contract awards to a company from USAspending.gov, with fields listed. Differentiates by scope and source, but does not explicitly name sibling alternatives, so not a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Mentions experimental status and cost but gives no explicit guidance on when to use vs alternatives. There is no mention of when not to use or comparison with sibling tools like lobbying or company_financials.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint (no mutation), so the description adds value by disclosing a per-call cost ($0.05) and noting that data is sourced from free EDGAR servers, with each filing identified by accession number. These details go beyond the annotations and help set expectations, though it doesn't mention rate limits or auth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the main purpose, followed by source context and a technical detail. It is concise, efficient, and well-structured, covering essentials without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It covers the core functionality, data source (EDGAR), a unique detail (accession number pinning), and cost. It doesn't explicitly mention output schema or limitations, but given the simplicity of the tool and the presence of an output schema (not shown), it is adequately complete. It could benefit from mentioning when not to use it (e.g., for historical filings), but that's not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema shows company (required) and limit (optional), but the description clarifies that 'company' refers to the subject of the Form 4 filings. It doesn't explain the 'limit' parameter beyond the schema's type/default, but it does mention 'latest' implying a default scope. The description lists output fields, which is not parameter semantics, so it adds limited value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose: parsing a company's latest Form 4 filings into structured data (who traded, role, buy/sell, shares, price, holdings). It specifies the resource (Form 4) and the action (parsed), and it stands apart from sibling tools like institutional_holdings or latest_filings by focusing on insider trades derived from Form 4.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives context (

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds valuable context: the cost per call ($0.05), the data included (top positions, shares, CUSIP, share of portfolio), and the scope (managers only). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (three sentences) and front-loaded with the core functionality. It includes cost and scope without fluff. The phrase 'Pinned by accession number' is slightly cryptic but not redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, the description covers what data is returned (shares, CUSIP, share of portfolio), the scope (managers, not operating companies), and cost. Since there is no output schema, it adequately describes the return content. The 'top' parameter default and max are in the schema, so no further detail is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing clear descriptions for 'company' (manager name or CIK) and 'top' (positions to return, default 20). The description reinforces 'company' by giving examples and mentions 'top positions by value', but adds no new parameter-specific syntax or constraints beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns an institutional manager's latest 13F-HR parsed and aggregated, listing top positions by value with shares, CUSIP, and share of portfolio. It explicitly distinguishes from operating companies, differentiating it from sibling tools like company_financials or lookup_company.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies it works on managers (Berkshire, Bridgewater...) and not operating companies, giving clear context for when to use it. It does not name alternative tools for operating companies, but the exclusion and mention of 'Pinned by accession number' imply a focused use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses a per-call cost of $0.01, states the ordering ('newest first'), and indicates the scope ('market-wide'). These add practical behavioral context not covered by annotations, though it does not mention pagination or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no redundant information. It front-loads the core purpose and adds a critical cost note, making it concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with optional parameters, and the description covers the main use case and key details like ordering and scope. Since there is no output schema, the description does not describe return fields, but for a listing tool this is acceptable; the context is sufficient for an agent to decide whether to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters, and the description does not add new semantic meaning beyond what the schema already provides. The mention of 'newest first' is a tool-level behavior, not parameter-specific, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists new S-1 and F-1 IPO registration statements from EDGAR, market-wide and newest first, specifically calling it the 'earliest public signal' of a US IPO. This is specific and distinguishes it from general filing tools like latest_filings or recent_filings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for tracking new IPO filings but does not explicitly mention when to use this over alternatives or when not to use it. It provides context ('market-wide, newest first') but lacks direct comparison with sibling tools, so guidance is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations declaring readOnlyHint and openWorldHint, the description adds meaningful behavior beyond them: 60-second upstream caching, inclusion of 8-K item codes, accession numbers for pinning, and a $0.01 per-call cost. This is valuable operational context for an agent deciding whether and how often to call the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences total, each carrying useful information: purpose, target use case, caching behavior, data payload highlights, and cost. There is no filler or repetition from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description partially compensates by naming key response features (8-K item codes, accession numbers). It covers caching, filtering, and cost. It does not fully describe the response shape or pagination, but for a simple pollable feed with two parameters, it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds only that the form filter is optional and that the feed is market-wide; it does not add new meaning for the limit parameter beyond what the schema already states. This is adequate but not a differentiator.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly identifies a market-wide SEC filing feed, establishes its real-time nature, and distinguishes it from sibling tools like recent_filings and edgar_search by emphasizing market-wide scope and 'as they land' behavior. It also adds differentiating details like 8-K item codes and accession numbers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the intended use case: 'Built for monitoring agents that poll' and provides the 60-second cache as a practical polling consideration. It also clarifies the optional form-type filter. It does not explicitly name alternatives or when not to use this tool, but the intended context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses additional behavioral traits: it is experimental, may change or be withdrawn, is not covered by the accuracy eval, and costs $0.05 per call. It also describes the output content and ordering, providing useful context for an agent. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, consisting of two sentences. The first sentence front-loads essential caveats (experimental, may change) before specifying the core function, and the second adds cost. Every sentence carries significant information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite lacking an output schema, the description covers the main output fields (registrant, income/expenses, issue areas), ordering, and experimental status. It also mentions cost. While it does not specify exact return format or pagination details, the description provides sufficient information for an agent to call the tool reasonably. Given the tool's experimental nature and simplicity, this is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters (company, year, limit) are already documented in the schema. The description adds marginal parameter context by mentioning 'for a client company' and 'newest first', but does not explain syntax or edge cases beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves US Senate LDA lobbying disclosures for a client company, specifying the key data fields (registrant, income/expenses, issue areas) and ordering (newest first). This is a specific verb-resource combination that distinguishes it from sibling tools like insider_trades or government_contracts, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lacks explicit guidance on when to use this tool versus alternatives. It only mentions being experimental and outside the core SEC path, which hints at limited reliability but does not name alternative tools or exclusion conditions. An agent must infer the appropriate use from the domain-specific wording.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description only needs to add extra context. It adds useful details: 'Free: no key and no payment needed' and 'Use it to verify the service before paying.' It also notes the US SEC scope. However, it doesn't describe rate limits, data freshness, or error behavior, which would be valuable for a public API tool. Since the bar is lower with annotations, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficient, front-loading the core purpose and then adding usage context. Each sentence contributes new information (purpose, when to use, scope, cost). It is not verbose, but contains a few separate clauses that could be tightened. Still, it remains well-structured and easily scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (one parameter, no output schema), the description adequately covers what the tool does, its scope, and prerequisites. It even lists the expected return fields. No critical information appears missing for an agent to decide whether to invoke it. The only minor gap is lack of explicit mention of error cases (e.g., invalid ticker), but that's not essential for initial selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description fully covers the parameter 'company' with examples (AAPL, 320193). The description adds no new meaning beyond the schema—it simply restates 'ticker or CIK.' Since schema coverage is 100%, the baseline is 3, and the description doesn't improve on it. No format details beyond the examples are provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Resolve') and resource ('a ticker or CIK to a company's canonical SEC identity'), and lists specific outputs (legal name, CIK, industry classification, tickers, exchanges). It distinguishes itself from sibling tools like edgar_search by positioning itself as the first step for ticker-to-CIK resolution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: 'Use this first when you only have a ticker and need the CIK for other calls.' Also notes 'US SEC registrants only,' which sets a clear exclusion boundary. While it doesn't name alternative tools, the context implicitly suggests it's the initial lookup before other SEC-related calls. Missing an explicit 'use other tools when' statement keeps it from a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds valuable information: it explicitly states the experimental status, potential for change or withdrawal, and the cost of $0.01 per call. These are behavioral traits not present in the annotations, enhancing transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single coherent sentence plus a short cost note. The experimental warning is placed at the front, which is useful for setting expectations. It is concise without being terse, and every sentence adds value (experimental status, core function, cost). Structure is logical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With two simple optional parameters and no output schema, the description provides the essential purpose and cost. However, it does not describe the output format (e.g., list of objects with market names and probabilities), which an agent might need to correctly interpret results. Given the absence of an output schema, the description should compensate more; the mention of 'implied probabilities' hints at output but is insufficient for full completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — both parameters 'q' and 'limit' are described in the schema ('Substring filter' and 'Markets to return. Default 10.'). The description only mentions 'optionally filtered by a question substring', which redundantly restates the 'q' parameter. It adds no new meaning beyond what the schema already provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as returning top-volume Polymarket markets with implied probabilities, optionally filtered by a question substring. It is specific about the resource (Prediction markets) and the function, and it is clearly distinct from sibling tools which focus on SEC filings and other financial data. The experimental caveat does not obscure the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives context that this is experimental and outside the core SEC path, which implies it is not recommended for critical workflows. However, it does not explicitly state when to use this tool versus alternatives, nor mention any other tool as an alternative. The 'experimental' note is a caution, but the description lacks direct usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and openWorldHint=true, and the description complements these by disclosing the index depth, the fact that the response notes when older history exists, and the $0.01 cost with no subscription but requiring a credit key or machine payment. This is rich behavioral context beyond what annotations offer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence adds value: first states purpose and output, second mentions optional filter, third explains scope and limitation, fourth clarifies it's canonical data, fifth covers cost and access. No filler, front-loaded with the core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 3 params and no output schema, the description sufficiently conveys what to expect (fields returned), the boundary (last ~1000 filings), and the commercial access model. It is complete for an agent to invoke correctly without needing additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already documents all three parameters with full descriptions (100% coverage). The description adds marginal value by reiterating the form-type filter and ticker/CIK options, but does not exceed what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists a company's most recent SEC filings and names the returned fields (form type, dates, accession number, URL). It distinguishes from siblings by defining the scope (EDGAR's recent-filings index, ~1000 filings) and positioning this as the canonical record, not commentary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context on when to use: for recent filings within the ~1000 limit, and for canonical records rather than commentary. It notes the limitation that older history is not searched, implying that other tools (e.g., edgar_search) may cover broader history, though it doesn't name them explicitly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description does not contradict them. Beyond annotations, it discloses cost ($0.10 per call), the counting rule for lightly reworded sentences (one removal plus one addition), the underlying sentence-level diff basis, and the former name. It does not describe rate limits or exact output format, but those are minor given the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences and front-loads the definition, then clarifies scope, then gives the sibling alternative, former name, and cost. Each sentence carries distinct and useful information, though the inclusion of both a former name and cost might be considered optional. Overall, it is well-structured and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must explain the return value and any implicit behavior. It states the result is a percent with a 'magnitude band' but never defines the band values or how they map to output. It also does not specify which years are compared (only 'year over year' without clarifying the base year selection). These gaps make it incomplete for an agent that needs to interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add explicit parameter-level meaning beyond what the schema states; however, it introduces the 'year over year' concept that implies the tool compares the latest filing to the prior year—a behavior not captured in the schema and not clarified further. This omission keeps it at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description defines the metric precisely: 'added sentences divided by total sentences in the newer section, as a percent, with a magnitude band'. It explicitly states what it measures (editing activity) and what it does not (risk/exposure), and names the sibling compare_filings as the alternative for raw passages. This leaves no ambiguity about the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides both positive and negative usage guidance: it says this measures editing activity, not risk or exposure, and explicitly directs users to compare_filings when passages are needed ('buy that when you need the passages themselves'). It also notes the former name still answers, aiding legacy users. This clearly routes an agent to the correct tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, which cover safety and open-world nature. The description adds valuable behavioral context beyond that: it is experimental, may change, cached for 60s, not an oracle, and costs $0.01 per call. This gives the agent important expectations about reliability and cost, which annotations do not convey. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the critical caveats (experimental, may change) before listing the data provided. Every phrase earns its place: the warning, the metrics, the caching, the oracle disclaimer, and the cost. No fluff or redundancy; it is concise yet information-dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description compensates by listing the key returned metrics (price, FDV, market cap, 24h volume), giving the agent a clear expectation of what to expect. It also covers practical aspects: caching, cost, and reliability (not an oracle). However, it does not specify units, formatting, or whether the response is a single object or includes additional fields. Still, for a read-only tool with strong annotations, it is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters, with chain and token each described. The description does not add parameter-specific semantics beyond what the schema provides, but it does clarify the kind of data (DEX-aggregated metrics) that the tool returns, which indirectly informs parameter meaning. Since the schema already documents both parameters, a baseline score of 3 is appropriate; the description adds no extra parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the function: providing DEX-aggregated price, FDV, market cap, and 24h volume for a token contract. It names the specific resource (token contract) and the data returned. While it does not explicitly contrast with siblings like token_report or who_holds, its focus on these specific metrics is distinct enough. The purpose is clear and specific, not a tautology.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides important context for usage: it warns the tool is experimental, outside the core SEC path, not covered by accuracy eval, and may change or be withdrawn. It also notes caching and that it is not an oracle, implying caution for critical decisions. However, it does not explicitly say when to use this tool versus alternatives, nor give conditions for when not to use it. The guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

While annotations already declare readOnlyHint=true and openWorldHint=true, the description adds substantial behavioral context: it is experimental, not covered by the accuracy eval, may change or be withdrawn, costs $0.10 per call, and relies on GeckoTerminal aggregated DEX data. It also discloses that it is not an oracle or financial advice. These details go well beyond the static hints and inform the agent about reliability, cost, and data source, which are critical for decision-making.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence that front-loads the critical experimental caveat before describing the tool's capabilities. It is appropriately concise for the amount of essential information conveyed (scope, data fields, data source, cost, disclaimers). While it is long, every clause serves a purpose, and the structure is logical — a minor optimization would be splitting into two sentences for readability, but it remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (returns multiple market metrics) and the absence of an output schema, the description fully enumerates the returned data fields (price, 24h change, FDV, market cap, 24h volume, supply, pool count, deepest pool liquidity, risk flags), so an agent knows exactly what to expect. It also covers cost, data source, and experimental status. Nothing essential is missing for a correct invocation or interpretation of results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage with clear descriptions for both parameters (chain and token). The description does not add parameter-specific detail, but that is not necessary given the schema's completeness. It does imply the token is an ERC-20 contract address and chain is one of three options, but these are already in the schema. Per the baseline rule for high schema coverage, a score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides 'one-call market data for an ERC-20 token' and enumerates the specific data points (price, 24h change, FDV, market cap, volume, supply, pool count, liquidity, risk flags). This distinguishes it from sibling token_price, which presumably focuses only on price, by signaling a comprehensive due-diligence snapshot. The verb 'report' and the explicit resource scope leave no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description frames this as a comprehensive alternative to single-purpose queries ('one-call market data') and explicitly warns it is experimental, outside the core SEC path, and may change or be withdrawn. It does not explicitly name alternatives like token_price or state 'use this when you need the full picture', but the wording strongly implies it for holistic token assessments. It also mentions it is not an oracle or financial advice, which guides appropriate usage expectations. A clearer 'when to use vs. token_price' would earn a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds valuable behavioral context: it is experimental, may change or be withdrawn, is not covered by the accuracy eval, and costs $0.05 per call. It also clarifies data semantics (exports total value vs general imports), which goes beyond the annotation-only baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the experimental warning, followed by a concise main clause stating the data and source, and ends with the cost. At roughly 40 words, every sentence earns its place; the structure is logical and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only data tool, the description covers source, units, frequency, scope, and direction definitions. It does not describe the output format (no output schema exists), but the data nature (values by partner) is reasonably inferable. The experimental and cost caveats add necessary context. Overall, it is complete enough for an agent to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%—all four parameters are documented with types, defaults, and examples. The description adds only minor clarification, such as 'one HS chapter' and 'monthly', which largely mirror the schema. It does not compensate for any gaps or add substantial meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns monthly US customs-reported trade values in dollars by trading partner for one HS chapter, from the Census international trade series. This specific verb-less but explicit resource and scope distinguishes it from all siblings, none of which mention trade flows or HS chapters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides important caveats—experimental status, instability, and cost—but does not explicitly state when to use this tool over alternatives or any exclusions. It implies usage for trade-data queries, but no alternative routing or 'when not to use' guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and open-world semantics; the description adds determinism, cost per call, and the output structure (verdict, as-reported value, accession number), which are not present in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences: purpose, return content, cost. No redundant information; front-loaded with the core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters and no output schema, the description explains return values and cost but does not cover parameter selection nuances (e.g., end vs fiscal_year) or prerequisites. However, those are in the schema, and the description is otherwise adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 7 parameters fully (100% coverage). The description adds no additional parameter-level details beyond saying the claim is numeric and that the verdict relates to claimed_value. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states a deterministic check of numeric claims against the company's own SEC XBRL filings, with specific verdict outcomes (supported/contradicted/unverifiable). This distinguishes it from general financial data tools like company_financials or compare_filings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context that this verifies claims against official XBRL filings, implying use for factual verification. However, it does not explicitly name alternatives or when-not-to-use, so it lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. Description adds meaningful context: the $0.05/call cost, the 'latest information table' freshness nuance, and the total count of managers. This goes beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences deliver all essential information: output contents, relationship to sibling, and cost. No fluff, perfectly front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity tool with two well-documented parameters and no output schema, the description covers purpose, output fields, pricing, and usage context. Could mention pagination or sorting but it's not essential.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with clear parameter explanations (ticker/CIK, limit default). The text doesn't add parameter-level detail, but none is needed; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it returns 13F managers and their fields (manager, CIK, filing date, accession number) for a company. The phrase 'The inverse of institutional_holdings' actively distinguishes it from a sibling tool, leaving no ambiguity about its function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the sibling 'institutional_holdings' as its inverse and suggests chaining them to walk from ticker to portfolios. This gives concrete when-to-use guidance and an alternative, satisfying the top criterion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description goes beyond this by adding costs ($0.10 per call), experimental status (may change/withdrawn), and explicitly stating 'No payment is signed or submitted.' It also clarifies the scope (one public endpoint, anonymous caller). This adds meaningful behavioral context without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense paragraph that front-loads the experimental warning, then states the action and output. It contains no fluff—every clause earns its place (e.g., the cost, the no-payment note). It could be split into clearer bullet points, but it's efficient and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has only one parameter and no output schema, so the description bears full responsibility for explaining the return value. It enumerates the exact components of the report (status, rails, headers, health checklist) and adds cost and experimental caveats. This is sufficient for an agent to understand what to expect, though it doesn't specify the exact response format (e.g., JSON) or any potential error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides a clear description for the single 'url' parameter ('Absolute https URL of the x402 resource') with an example. Schema description coverage is 100%, so the baseline is 3. The tool description reiterates that the endpoint must be public and HTTPS, which slightly reinforces the parameter's constraints but doesn't add new semantic detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Inspect') and a precise resource ('one public HTTPS x402 endpoint'), then enumerates exactly what it reports: HTTP status, payment rails, WWW-Authenticate header, Bazaar discovery extension, and a health checklist. This fully distinguishes it from the other finance/filings/crypto siblings, all of which serve different data domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states what the tool does but does not explicitly say when to use it versus alternatives, nor does it mention any sibling tool for comparison. It does imply usage (for auditing an endpoint's 402 challenge) and notes that it's experimental, but there is no 'when not to use' or alternative routing. Since the tool is unique among siblings, the omission is less critical, but explicit guidance would still be an improvement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.