toolgrep

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

Annotations already declare readOnly=true, idempotent=true and openWorld=false, so the safety profile is covered. The description adds real value beyond that: the explicit bound of 2-6 products and the disclosure that results include full records plus a field-by-field table keyed by slug. It does not cover failure modes (e.g., unknown slug handling), which keeps 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?

Two tight sentences, zero filler, with the comparison scope front-loaded and the return shape second. Every clause carries information an agent can act on.

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 explained, yet the description still summarizes the response shape. Combined with annotations covering safety and a single fully documented parameter, nothing an agent needs to invoke this correctly 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?

Only one parameter, fully described in the schema (including minItems 2 / maxItems 6), so schema coverage is effectively 100%. The description's '2 to 6' merely restates the schema constraint and adds no semantics beyond it. 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?

Specific verb (compare / side by side) plus resource (products) and an explicit enumeration of the comparison dimensions: pricing, free tier, API, MCP, SDK, open source. It implicitly separates itself from single-record siblings like get_product, but never names find_alternatives or search_products, 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?

The '2 to 6 products' framing implies the usage context (batch comparison of a short candidate list) but there is no explicit when-to-use, when-not-to-use, or routing to alternatives such as find_alternatives for discovery vs. this tool for head-to-head comparison. Usage is inferable but not stated.

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 read-only/idempotent/closed-world, but the description adds genuinely useful behavior beyond them: results are nearest neighbours of the product's embedding, and there is a fallback to same-category matching when the vector index is unavailable. That fallback materially affects result interpretation. It stops short of noting ranking or result-count behavior.

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 tight sentences with no filler; the core behavior is front-loaded and the fallback caveat follows. 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?

With an output schema present, return values need not be explained, and the filters are fully covered by the schema. The fallback note closes the main behavioral gap; only ranking/ordering detail is absent.

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 86%, so the schema already documents slug and each filter flag. The phrase 'with optional filters' adds nothing beyond what the schema provides, so the baseline 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?

States a specific outcome ('products similar to a given one') plus the mechanism ('vector similarity'), which distinguishes it from search_products and compare_products without naming them. It is clear what the tool returns, though it never explicitly contrasts itself with its siblings.

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 the use case (finding alternatives to a known product slug) but gives no explicit when-to-use vs search_products or compare_products, and no prerequisites. Usage is inferable rather than stated.

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 openWorldHint=false, so the safety profile is covered. The description adds useful nuance that the owner's agent_notes are returned conditionally ('when the listing has them'), but says nothing about auth needs, rate limits, or error behavior.

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 tight sentence that front-loads the resource and scope and mentions the notable conditional return field. Every clause earns its place 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?

For a simple one-parameter getter with a full output schema and safety annotations, the description covers scope and a return-content nuance adequately. It could be slightly stronger with guidance on when to prefer search_products, but nothing critical to invoking it correctly 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% and the schema already documents slug with a source_url format hint. The description's 'by slug' simply reinforces the single required parameter without adding format or syntax detail, so the baseline 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 states a specific verb (retrieve) and resource (one product) scoped by slug, with 'one product' implicitly contrasting against the plural search_products sibling. It is clear what the tool does, though it never explicitly names or differentiates from find_alternatives/compare_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 'by slug' phrasing implies usage (you already have a known slug), but there is no explicit when-to-use, when-not-to-use, or routing to search_products for discovery. Usage is left to inference.

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 safety (destructiveHint=false, idempotentHint=true), but the description adds real behavioral context the annotations cannot: that a re-crawl is throttled to once per hour per product, and that the report itself is always recorded even when the re-crawl is skipped. It still omits what response/confirmation the caller gets back.

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 padding, and the core action is front-loaded before the rate-limit caveat. Every clause adds information an agent needs.

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, return values need not be described, and the description covers the key operational caveats (throttled re-crawl, guaranteed report record). The remaining gap is failing to identify what 'slug' refers to, which is the one required input.

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?

At 50% schema coverage the description needed to compensate but says nothing about parameters. The required 'slug' has no description anywhere, so an agent must guess whether it is a product slug, URL path, or internal listing id, and the description never explains what the optional 'reason' is for.

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 ('flag a listing as outdated or wrong') plus the immediate side effect ('triggers a re-crawl'). No sibling tool (compare_products, find_alternatives, get_product, search_products, submit_product) does anything similar, so an agent can distinguish it on sight.

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 trigger condition is implied by the words 'outdated or wrong', which tells an agent broadly when to reach for it, but there is no explicit when-not guidance, no prerequisites, and no named alternative (e.g. correcting via submit_product instead of reporting).

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 the safety profile (readOnly, idempotent, closed-world). The description goes beyond them by disclosing the result shape: up to `limit` products plus a separate `sponsored` list, and that results combine full-text with semantic similarity. It does not mention ranking, pagination, or empty-result behavior.

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: what it searches, how to phrase the query, and what comes back. The most decision-relevant information (query mode and filters) is front-loaded, and the result-shape caveat is last.

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 needn't explain return values, yet it still flags the `sponsored` list — a meaningful behavioral detail. What's missing is guidance on the sibling tools and on whether results are ranked or paginated, which matters for a search entry point.

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 86%, so the baseline is 3, but the description adds real value: the default (10) and cap (50) for `limit` are not in the schema, and it enumerates the filter dimensions (category, free tier, API, MCP, open source) in one place. It adds nothing further on the query semantics beyond match mode.

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 ('search the directory') plus the two search modes (natural-language query and structured filters), which is more precise than the title. It does not name or differentiate itself from siblings such as find_alternatives or compare_products, so an agent must infer the boundary.

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 useful usage context — phrase the query like a need, and omit the query to browse by filters only — which implies when this tool is appropriate. However, it never states when NOT to use it or which sibling to pick instead (e.g. find_alternatives for substitutes, get_product for a known item).

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, open-world, idempotent, non-destructive operation, so the bar is lower. The description still adds real value beyond them: no authentication is required, the crawl is asynchronous with an expected ~1 minute latency, and status_url should be polled for completion.

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 with zero filler; the core action and the no-account constraint are front-loaded, and the polling instruction is a tight actionable follow-up.

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 two-parameter write tool with an output schema available, the description covers the essentials: action, auth requirement, async timing, and how to check completion. It stops short of describing duplicate-submission behavior or what to do if the crawl never completes.

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, so the schema already explains url and the optional claim email. The description only restates that a product URL is submitted and adds no format, normalization, or validation semantics 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?

Specific verb and resource: 'Submit a product URL to be crawled and listed,' which clearly separates it from the read-oriented siblings (get_product, search_products, compare_products). It does not explicitly name an alternative, but no sibling competes for this write action, so confusion risk is low.

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?

Use is implied (you call this when you want a product listed) and the description helpfully says 'No account needed' and to 'poll status_url' afterward. However, it never states when NOT to use it, nor what to do if a listing already exists or if the crawl fails.

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