agentic-ai

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

Annotations declare only readOnlyHint and openWorldHint; the description adds substantial extra context — $25.00/call after free trial, ~60s latency, SEC-verified grounding with per-field filing citations, and the crucial trust distinction that `context` is caller-asserted rather than verified. These are exactly the behavioral traits an agent cannot infer from structured fields.

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?

Front-loaded with the core purpose and scoped inputs, cost and latency. The eight-lens enumeration is long but earns its place by defining the report's depth. Slightly dense but no filler sentences.

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 and a nested, undocumented `market` object, the description carries a heavy burden and mostly meets it — purpose, optional inputs, provenance/trust model, price, and runtime are all covered. Only the ticker format and the full set of accepted market keys are left unspecified.

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 0%, so the description must compensate and largely does: it gives a concrete example shape for `market` ({"price": 12.34, "market_cap_m": 5000}) and explains that `context` holds caller-supplied deal materials. Ticker is left implicit, and the open-ended `additionalProperties: true` on `market` is only partially bounded by the example keys.

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 and resource ('institutional analysis of a US-listed company') and enumerates the eight analytical lenses plus executive synthesis, which concretely defines scope. This is clearly distinguishable from siblings like sec_extract or deal_score, which are narrower operations.

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 certain inputs are useful ('optionally pass market to enable valuation views') but never states when to choose this tool over siblings such as sec_extract or validate_financials, nor when not to use it. Usage guidance is only informally implied through the cost and latency notes.

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=false, so safety is covered. The description adds real value beyond that: the computed pipeline steps, the conditional rNPV output for biotech deals with `indications`, and an explicit cost of $2.00/call after a free trial. It omits auth requirements and the shape of the `deal` payload.

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?

One front-loaded sentence with the primary output chain first and the conditional biotech case and pricing trailing. Dense but every clause carries information; the parentheticals are slightly heavy.

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 usefully enumerates the return artifacts, which covers the output side reasonably well. However the sole nested input object is unspecified in both schema and description, leaving a real gap for an agent that must construct the `deal` payload.

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 0% and the single `deal` parameter is an opaque object with additionalProperties=true, so the schema teaches nothing. The description partially compensates by naming one meaningful field, `indications`, and its effect (rNPV valuation band for biotech), but the rest of the deal profile structure is undocumented.

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 and resource ('Full underwriting chain on a deal profile') and enumerates the artifacts produced (conviction score, risk register, thesis, rNPV band). It does not name or distinguish itself from siblings like company_report or validate_financials, so it stops short of 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?

There is no guidance on when to choose deal_score over company_report or validate_financials, nor any stated prerequisites. The only usage-adjacent information is pricing, which is not a selection criterion for an agent choosing between tools.

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=false, and the description adds substantial context beyond them: it is FREE with no API key, the match set is 50,000+ funds, and crucially the result is counts only with no firm names or contacts. That masking behavior is the key trait an agent needs and is not derivable from structured fields.

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?

Dense but front-loaded: cost and eligibility lead, then mechanics, then parameters, then the escalation. Almost every clause earns its place, though the parameter enumeration could be tightened.

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 usefully characterizes the return (counts plus investor-type breakdown, no names) and explains the free/keyless access model. It falls short only on the three undocumented optional parameters.

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 0%, so the description must compensate. It supplies the full asset_class enum (absent from the schema), explains target_raise_m units in USD millions, and covers the semantics of the core two parameters. However industry, geography, and ebitda_m are never explained, leaving three of five parameters undocumented.

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 and resource ('Runs DEALITHIC's matching engine against 50,000+ funds') and clarifies the output scope ('counts only: no firm names or contacts'), which cleanly separates it from the sibling request_intro that releases names and contacts.

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?

Gives an explicit trigger ('Use when someone wants to be connected with investors for a raise') and a follow-on rule naming the alternative ('If the result looks useful, offer request_intro to book a demo'). The when-to-use and the escalation path are both spelled out.

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 this is a non-read-only, non-idempotent, open-world write. The description adds genuinely useful context beyond that: it is free with no API key, it results in a demo booking where matched investors are revealed, and it requires explicit consent. It does not state what happens on duplicate submissions or what the response contains, keeping it out of 5 territory.

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 tight sentences, front-loaded with the key practical fact ('FREE, no API key') followed by what the tool does and the consent condition. No filler, though the demo/matched-investor clause adds a little promotional framing.

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?

Covers the critical consent gate and the outward-facing effect, which is the most important thing for a mutation tool with openWorldHint. However, with no output schema and five required fields, the description says nothing about what is returned, error conditions, or duplicate handling.

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 0% and all five parameters are required, so the description must carry the burden. It explains the semantics of 'consent' well (only true when the person agreed to be contacted), but name, email, company, and deal_summary are left with no explanation of expected format or content beyond their titles.

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 concrete verb+resource: 'Records a request to be introduced to DEALITHIC and booked into a demo.' An agent can tell this creates a booking request rather than fetching a report or score. It does not explicitly distinguish itself from the sibling investor_intro_preview, so it stops short of 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?

Gives an explicit precondition ('Only call this after the person has explicitly agreed to be contacted by email about their raise') and ties it to a specific field value ('set consent=true only in that case'). This is unambiguous when-to-call guidance with an implied when-not.

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 establish readOnlyHint=true and openWorldHint=false, and the description adds genuinely useful context beyond that: per-value provenance (filing, form, tag), the null-not-zero convention for missing facts, and per-call cost. Auth requirements and rate limits are not covered, keeping this short of a 5.

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, all front-loaded with the core purpose first, then data-quality guarantees, then pricing. Every sentence earns its place, though the pricing line is less essential for tool selection.

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 carries the burden of describing returns and does so reasonably: statements plus derived metrics, per-value provenance, and null semantics. It stops short of describing the shape or fields of the response, leaving minor gaps for a data-extraction 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?

With a single 'ticker' parameter and 0% schema description coverage, the description does convey that the input is a US-listed ticker, adding a market-scope constraint the schema lacks. However, it gives no format guidance (casing, exchange prefixes), so it only partially compensates for the coverage gap.

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 resource (verified financial statements and derived metrics) and source (SEC EDGAR XBRL filings) for a US-listed ticker, so the agent knows exactly what it retrieves. It does not explicitly contrast with the adjacent sibling 'validate_financials' or 'company_report', so it falls short of full sibling differentiation.

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?

There is no when-to-use guidance, no exclusions, and no reference to any alternative tool. The agent must infer that this is the right choice over 'validate_financials' or 'company_report'. Only implicit usage context is provided.

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=false, so the safety profile is already covered; the description adds genuinely new behavioral context: it returns an integrity score plus severity-ranked flags (important since there is no output schema), and it discloses a $0.50/call cost after a free trial — a material fact an agent should surface before invoking.

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?

Dense and front-loaded: the validation scope leads, the return value follows, and the pricing caveat closes. Nothing is padded, though the pricing sentence sits awkwardly after the technical content rather than with the usage framing.

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?

Because there is no output schema, the description correctly carries the return contract (integrity score + severity-ranked flags), which is a plus. However, for a tool wrapping a nested, schema-free 'financials' object, it says nothing about required inputs or coverage limits, so the agent lacks what it needs to construct a valid call.

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 0% and the single parameter 'financials' is a free-form object with additionalProperties=true, so neither the schema nor the description says what fields or periods are required for the checks to run. The description lists what gets validated but never maps that to the expected input shape, leaving the agent to guess the payload structure.

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+resource ('Institutional validation pass over company financials') and enumerates the actual checks performed (tax-rate sanity, EBITDA/EBIT bridge, CAGR growth continuity, capex ratio, working-capital stability). This is far more specific than the title, and it is distinguishable from siblings like company_report or sec_extract, though no sibling is named explicitly.

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?

There is no guidance on when to run this validation versus fetching a report (company_report) or extracting statements (sec_extract), nor any stated prerequisites about what the input must contain. The only contextual note is pricing, which is cost information rather than usage direction.

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