ironscout

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

Annotations declare readOnlyHint and openWorldHint, which are consistent with the tool's read-only nature. The description adds valuable behavioral details: it is purely descriptive (no forecast), returns NOT_FOUND when no snapshot exists, and includes methodology and sample counts. This fully informs the agent of the tool's behavior 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?

The description is two concise sentences. The first sentence defines the purpose and output; the second clarifies limitations and error behavior. No extraneous information, 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?

Given the tool has only 2 parameters, no output schema, and rich annotations, the description covers all necessary aspects: what data is returned, constraints on windowDays, error behavior, and non-forecast nature. It is complete for an agent to correctly invoke the 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% and already describes both parameters clearly (caliber with example, windowDays with allowed values and default). The description adds the context of a 'rolling window' but does not repeat schema details, which is appropriate. The description adds value by explaining the overall window concept.

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 a clear verb ('get') and resource ('caliber market snapshot'), and details the output: price distribution statistics (median, p25, p75, min, max) over a rolling window. It clearly distinguishes from sibling tools by focusing on market-level descriptive statistics.

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 that the tool provides only descriptive statistics, never a forecast or recommendation, guiding when to use it. It also mentions the error condition for missing snapshots. However, it does not explicitly name alternative tools for other use cases, though siblings are listed separately.

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 readOnlyHint and openWorldHint annotations, the description discloses error handling (NOT_FOUND) and return content (offers), adding useful 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?

Two sentences, zero waste, front-loaded with key 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?

For a simple single-parameter read tool, it covers purpose, return format, and error cases; could be more explicit about offer details but 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% with a good parameter description; the tool description adds no new parameter semantics beyond restating the ID.

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 a single product by ID with offers, but does not differentiate from siblings like search_offers or get_market_snapshot.

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; no exclusions or context 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 mark it as read-only and open-world. The description adds that calibers without snapshots are still included with hasSnapshot: false, providing useful behavioral details beyond annotations. 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?

The description is concise: two sentences with no unnecessary words. It front-loads the main action and output details efficiently.

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 no parameters and simple purpose, the description is largely complete. It explains the output fields and behavior for missing snapshots. It could mention ordering or pagination, but 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?

No parameters exist, so the description naturally doesn't add parameter info. Following the baseline rule for 0 parameters, a score of 4 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 the verb 'Enumerate' and the resource 'every canonical caliber IronScout recognizes'. It also explains the output includes whether a snapshot exists and sample count, distinguishing it from sibling tools that deal with specific snapshots or products.

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 usage context is implied: it's for listing all calibers. However, there is no explicit guidance on when to use this tool versus alternatives like get_market_snapshot, nor 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?

Beyond annotations (readOnlyHint, openWorldHint), description adds key behavioral detail: ineligible retailers are omitted entirely (fail-closed). This is not evident from annotations alone.

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 sentences, front-loaded with purpose, no wasted words. Each sentence contributes meaningfully.

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 parameterless list tool without output schema, the description fully covers purpose, eligibility behavior, and nature (descriptive directory). 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?

No parameters (baseline 4). Description adds value by explaining the tool is a directory without needing params.

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 lists eligible/visible retailers. Specific verb-resource combination distinguishes from siblings like list_calibers. Mentions fail-closed behavior ADR-005.

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: descriptive directory only, but does not explicitly state when not to use or mention alternatives like search_offers for more advanced filtering.

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 value by elaborating on the read-only nature (descriptive only, no scores) and warns against rewriting outUrl, with 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?

Two well-structured sentences: first covers purpose and result nature, second provides key usage instructions. Every sentence 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 the 11 parameters, no required fields, and no output schema, the description covers the return format (prices, availability, etc.) and core behavior. It could detail pagination but is sufficient for agent 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?

Schema coverage is 55% (moderate). The description reinforces the sort parameter's mechanical nature but adds no new information for other parameters 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 searches canonical ammunition products and their per-retailer offers, with a specific verb and resource. It distinguishes itself from sibling tools like get_product (single product) and list_retailers (retailers only).

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 explains results are descriptive only (no verdicts) and provides specific usage instructions for outUrl and sort. While it doesn't explicitly state when not to use this tool, the sibling context and clear scope make it effective.

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