13FLOW

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

Annotations already declare readOnly, openWorld, idempotent, and not destructive. The description adds value by revealing that scores are ordinal screens, not forecasts, which informs agent expectations beyond the safe-read hints.

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?

Two concise sentences with no wasted words. Front-loads the purpose and adds a critical caveat, making it efficient for quick comprehension.

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 core purpose and output interpretation, and the output schema exists. However, the tool has 10 parameters with no details in the description, and the screening context is vague, leaving gaps for a complex 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 0% schema description coverage, the description must compensate, but it only mentions 'explicit filters' generically. It provides no individual parameter roles, allowed values, or constraints, leaving the agent with 10 undocumented parameters.

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 ranks watchlist candidates with explicit filters, and clarifies that scores are ordinal research screens. It distinguishes the tool's purpose but does not explicitly differentiate from sibling 'preview_watchlist'.

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?

Implies usage for filtering and ranking watchlist candidates, but lacks explicit guidance on when to use versus alternatives like 'preview_watchlist', or conditions to avoid.

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 safe read-only behavior. The description adds value by detailing what data is not stored (no IP, user-agent, etc.), enhancing transparency 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 concise two sentences that front-load the action and essential details, with no unnecessary words.

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, together with annotations and output schema, covers the tool's purpose and constraints. It lacks mention of update frequency or caching but is otherwise 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?

With zero parameters, the description appropriately focuses on the tool's output and behavior. No additional parameter information is needed.

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 aggregate 7/30-day MCP usage, fixed client families, tool mix, and reliability. It specifies what is included and what is not stored, distinguishing it from sibling tools like get_data_quality or get_confluence_methodology.

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 aggregate statistics and clarifies privacy aspects (no IP, user-agent, etc.), but does not explicitly contrast with sibling tools or state when not to use it.

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, idempotentHint=true, and destructiveHint=false. Description adds value by noting the contract is 'frozen' (implying immutability) and lists included details (proof boundary, validation requirements), providing behavioral context beyond 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?

Single sentence is concise and front-loaded with the key action and resource. Every word adds value with no 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 zero parameters, rich annotations, and presence of an output schema, the description fully informs the agent about what the tool does and its safety profile. No missing information needed for tool 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?

Tool has no parameters, so baseline score is 4. Description need not add parameter information, and schema coverage is 100% trivially.

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 the tool returns the 'frozen Confluence v1 methodology contract' with specific content ('proof boundary and validation requirements'). Verb 'Return' identifies the action, and the resource is distinct from any sibling tool.

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?

No direct guidance on when to use this tool vs alternatives. However, since no sibling tool appears related to methodology, the lack of explicit guidance is not penalized heavily. Score reflects missing context like prerequisites or typical use cases.

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 readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description still earns credit by disclosing interpretive traits an agent cannot get elsewhere: scores are ordinal heuristic ranks rather than probabilities, and diagnostics are capped at 10 examples per category with available vs. returned counts. It does not state cache freshness or staleness, which is the one relevant omission.

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 short sentences, front-loaded with the core action, and every clause carries information (cached scope, ordinal-score caveat, diagnostics shape). Slightly dense in the final clause but no filler.

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?

An output schema exists, so return values need not be enumerated, yet the description still usefully sketches the diagnostics payload. Combined with full schema coverage and explicit annotations, only cache freshness and sibling routing are missing for a two-parameter read 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?

Schema coverage is 100% — both 'limit' and 'window' have descriptions including ranges and defaults — so the schema does the parameter work. The description adds nothing about limit/window semantics, so the 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?

States a specific verb and resource ('Return public cached Confluence v1 signals') and names the domain clearly enough to separate it from fund/stock siblings. However, it never distinguishes itself from the close siblings get_confluence_methodology and get_signal_history, so an agent still has to guess which of the three to call.

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 statement of when to use this tool versus get_signal_history (historical signals) or get_confluence_methodology (how the scores are built). The mention of 'source_url for full API details' hints at a follow-up path but is not a usage rule, leaving selection to inference from the name alone.

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 description adds context beyond annotations by clarifying that the warnings are review signals and never automatic corrections. This complements the annotations (readOnlyHint, destructiveHint) with practical usage intent.

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?

Two short sentences with no filler text. Front-loaded with the core purpose, and every word 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?

While annotations and an output schema exist, the description fails to cover the parameters, which is a significant gap. The tool is simple, but missing parameter semantics reduces 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?

The input schema has 2 parameters (limit, threshold) with 0% schema description coverage. The description does not mention or explain these parameters, leaving the agent without guidance on how to configure the request.

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 'public read-only data-quality warnings' and distinguishes them from 'automatic corrections'. The verb 'return' and resource 'data-quality warnings' are specific and differentiate from sibling tools that retrieve other types of data.

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 indicates these are review signals, not corrections, implying the tool is for observational use. However, it lacks explicit guidance on when to use this tool versus siblings, and no alternative tools are mentioned.

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 readOnly, openWorld, idempotent, not destructive. Description adds 'bounded' implying limits, which aligns with parameters. Adds moderate context beyond 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?

Single sentence with clear structure, no redundancy. Could be slightly more detailed without becoming 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?

Output schema exists but content unknown. Annotations cover safety. Description adequately explains core functionality but lacks detail on parameter behavior and response structure.

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 25% (only cik described). Description hints at parameters via 'positions, moves and history counts', but doesn't explain the limit parameters explicitly. Compensation is partial.

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 retrieves a bounded public fund portfolio by SEC CIK, listing included data types. While it doesn't explicitly differentiate from sibling get_* tools, the term 'fund portfolio' implies a specific resource.

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?

No guidance on when to use this tool versus alternatives like get_stock or list_funds. No when-not-to-use or prerequisite information 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 already declare readOnlyHint, idempotentHint, etc. The description adds that the state is 'verifiable' and lists specific returned fields, providing moderate additional context. 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?

Single sentence with front-loaded key purpose and enumerated details. Efficient, though could benefit from minor structuring for readability.

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 zero parameters and presence of an output schema (inferred), the description sufficiently covers what the tool returns. No significant gaps for a simple status query.

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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter information. Baseline 4 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 verb 'Return' and specifies the resource 'public state' with enumerated fields (LIVE/DEMO/DEGRADED, commit, etc.), making the tool's purpose unambiguous and distinguishing it from sibling 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?

No explicit guidance on when to use this tool versus alternatives (e.g., get_product_status or get_data_quality). The context signals indicate no parameters, but usage context is left unaddressed.

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 provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, fully disclosing safety and behavior. The description adds no extra behavioral context (e.g., no mention of rate limits, authentication, or side effects). With annotations doing the work, a 3 is appropriate.

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?

Single sentence, front-loaded with 'Return', no fluff. Every word 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?

With an output schema present, the description need not detail return values, but it lists key components helpfully. No mention of error cases or prerequisites, but for a parameterless read-only tool, this is nearly sufficient.

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?

There are zero parameters, so schema coverage is 100% by definition. The description adds value by listing the specific data returned (e.g., 'go-to-market readiness, sellable boundaries'), enriching the meaning beyond the empty 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 'go-to-market readiness, sellable boundaries, validation status and blocked full-quant artifact' using the verb 'Return'. This is specific to product status and distinguishes it from sibling tools like get_live_status or get_research_readiness.

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?

No explicit guidance on when to use this tool vs siblings. Implicitly it is for product status queries, but no exclusions or alternatives are mentioned. Given the sibling list includes many get_* tools, more context would help.

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, idempotentHint, and destructiveHint false, covering safety. The description adds that the returned data is 'current' and excludes commercial claims, providing useful behavioral nuance beyond the annotations. No contradictions.

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 no wasted words. It is front-loaded with the main action and clearly states the resource and exclusions. Every sentence 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?

Given the tool has no parameters, an output schema exists (though not shown), and the description mentions four components of the boundary. However, the term 'boundary' remains vague and could benefit from elaboration on what it specifically represents (e.g., thresholds, flags). Completeness is adequate but not fully transparent.

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 tool has zero parameters and 100% schema coverage. With no parameters, the baseline is 4, and the description does not need to add parameter information. It correctly focuses on the returned resource.

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 uses the specific verb 'return' and identifies a clear resource ('current research, validation, data-quality and operator-review boundary'). It also explicitly excludes commercial claims, which helps differentiate from siblings like get_data_quality. However, the term 'boundary' is somewhat abstract and could be more concrete.

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 like get_data_quality or get_confluence_methodology. Usage context is only implied by the description's focus on a combined boundary, but no direct comparisons or exclusion criteria 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 confirm readOnly, idempotent, and non-destructive. The description adds 'append-only' and 'revisions' which provide behavioral context beyond annotations. No contradictions.

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 that is front-loaded with action and purpose. Every word contributes meaning with no 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?

While the description and annotations together provide good behavioral context and purpose, the complete absence of parameter descriptions (given 0% schema coverage) leaves the tool's usage partially unclear. Despite having an output schema, the parameter gap detracts from 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?

The input schema has 3 parameters (limit, ticker, window) with 0% schema description coverage. The tool description does not explain any parameter's meaning, leaving the agent to infer from name and context. This is a significant 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 clearly states 'read append-only Confluence signal revisions' with a specific verb and resource. It distinguishes from sibling 'get_confluence_signals' by emphasizing revisions and append-only nature.

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 usage 'for audit and replay', providing clear context. It implicitly differentiates from 'get_confluence_signals' (likely current signals), but does not explicitly state when not to use or list 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 declare readOnlyHint=true, idempotentHint=true, making the tool's read-only nature clear. The description adds context about bounded results and data types, but does not disclose additional behavioral traits like rate limits or pagination. With annotations covering safety, this is adequate but not exceptional.

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, front-loaded sentence of 18 words with no redundancy. Every word adds value, making it 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?

Although an output schema exists, the description omits details on parameter usage and fails to explain 'bounded' behavior. For a tool with four parameters and minimal schema descriptions, it is incomplete and could mislead agents.

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 only 25% (only 'ticker' has a description). The tool description adds no detail about 'holder_limit', 'movement_limit', or 'include_quality_details'. The term 'bounded' hints at limits but does not explain parameters. Given low coverage, description should compensate but fails to do so.

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 specifies the verb 'Get' and resource 'one ticker', listing returned data types: 13F holders, quarter moves, quality warnings, and ordinal research score. This clearly states what the tool does, but lacks explicit differentiation from sibling 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?

There is no guidance on when to use this tool versus alternatives. The description does not mention prerequisites, limitations, or scenarios where another tool would be more appropriate.

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, idempotent, open-world, and non-destructive behavior. The description adds that results are 'compact summaries,' which aligns with the annotations. No contradictions, and the description adds modest context beyond 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?

Two efficient sentences, no wasted words. The first defines the tool's action, the second offers guidance for a related tool. Perfectly front-loaded and compact.

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 that the tool has an output schema (not shown), the description need not detail return values. It mentions pagination indirectly ('page through'), and the parameters for pagination are well-defined in the schema. A slight gap: it doesn't explicitly state that results are a list of summaries, but the output schema likely covers this.

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 description does not explain any parameters. Schema description coverage is low (33%), with only the 'query' parameter having a description. The description should compensate for this gap but fails to do so, leaving the agent with no additional 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 it searches and pages through compact tracked 13F manager summaries, specifying the resource ('tracked 13F manager summaries') and verb ('search and page through'). It distinguishes from the sibling tool 'get_fund' by directing users there for positions and moves.

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 a clear alternative ('Use get_fund for positions and moves'), implying when not to use this tool. However, it does not explicitly state scenarios where list_funds is preferred or excluded, though the context is sufficient.

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 provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds behavioral context by specifying the evaluation criteria (13F flow, quality gates, triggers), which goes beyond the 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?

The description is a single sentence that is front-loaded and concise. It could be slightly improved by breaking into smaller parts for readability, but it effectively communicates the core purpose.

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 has 3 parameters and an output schema, the description is reasonably complete for a read-only evaluation tool. It covers the main purpose and key input dimension (number of tickers), though missing parameter details for 'movement_limit' and 'include_quality_details' slightly reduces 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 0%, but the description only explains the 'tickers' parameter implicitly via 'Evaluate 1 to 25 tickers'. The other parameters ('movement_limit', 'include_quality_details') are not mentioned, leaving their purpose unclear despite default values and constraints in 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 verb 'Evaluate' and the resource '1 to 25 tickers', specifying the evaluation context 'against trusted 13F flow, quality gates and explainable watch/monitor/block triggers'. This distinguishes it from sibling tools like discover_watchlist and get_stock.

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 clearly indicates when to use: when evaluating tickers against specific criteria. However, it does not explicitly state when not to use or mention alternative tools, though the context of 12 sibling tools provides implicit guidance.

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