stierproducts tier lists

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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds beyond that by disclosing that the tool will refuse (not answer misleadingly) if products lack a shared category, which is a behavioral trait not captured in annotations. A 4 is appropriate as it adds meaningful context without covering all possible edge cases.

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: the first states the core action, and the second provides a crucial constraint. Zero wasted words, front-loaded with purpose, and 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's low complexity (1 parameter, 100% schema coverage, no nested objects, clear annotations, and an output schema), the description is complete. It covers the purpose, constraints, and refusal behavior, leaving no significant gaps for an agent to misinterpret.

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 'slugs' parameter is described as 'Product slugs to compare'), so the baseline is 3. The description adds minimal extra meaning beyond the schema, only implying that slugs must be from a shared category. The description does not elaborate on format or validation, but the schema is sufficient.

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 a specific verb ('Compare') and resource ('two to five products side by side'), clearly distinguishing it from siblings like 'get_product' (single product) and 'search_products' (search). It also explicitly states a constraint: they must share a category, preventing confusion with cross-category 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 explicitly states when to use this tool (compare 2-5 products) and when not to use it ('a mixed request is refused'), providing clear exclusion criteria. It also references sibling behavior implicitly by noting that comparing across boards is meaningless, helping the agent avoid misuse.

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 destructiveHint: false, which align with the description of a retrieval tool. The description adds value by detailing the depth of data returned (e.g., sentiment breakdowns, verbatim quotes) and mention of citation pagination via offset. This goes beyond the 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, dense paragraph that front-loads the purpose and cascades into details. Every sentence adds value, but the length is slightly verbose with a very long list of included fields, which could be more terse. Still efficient overall.

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 output schema exists, the description does not need to detail return types. It covers the key inputs and the richness of the output, with pagination hints. The only gap is the lack of mention about required permissions or data freshness, but with readOnlyHint set, it's acceptable.

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 coverage: slug is required, citation_limit and citation_offset have defaults and bounds. The description does not add significant meaning beyond what the schema offers, but it does hint at how citation_limit affects the breakdown ('always count every source regardless of this'), which is a minor addition. 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 explicitly states it retrieves 'one product' with extensive details like placement, verdict, pros and cons, GTIN barcodes, announcement date, breakdown of source sentiment, and full citations. This clearly distinguishes it from siblings like search_products (which would find products) or compare_products (which would 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 ends with 'Use this when a claim needs backing up,' providing a specific use case. However, it does not explicitly state when not to use it or mention alternatives among siblings, such as using get_tier_list for a simpler overview. The context is clear but lacks 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=true and destructiveHint=false. The description adds behavioral context: it returns a comprehensive set of fields including optional announcement dates and lists specific data points, which helps the agent understand the output richness without contradicting 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 tightly packed sentences. The first defines the output scope and content; the second establishes hierarchy with a sibling tool. Every word earns its place, no 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?

For a read-only list tool with a clear output schema, the description fully explains what is returned, how it fits among siblings, and when to use it. No gaps in guidance or behavioral 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 coverage is 100% and the schema descriptions already explain the parameters (category slug, optional tier filter). The description does not add significant new semantic information beyond 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 returns 'the full S-to-F tier list for one category' with specific fields, and distinguishes itself as 'the primary tool' that answers 'what is the best X' completely, differentiating it from siblings like get_product and search_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 description explicitly says 'This is the primary tool' and advises 'Call get_product for the quotes behind a placement,' providing a clear alternative. It implies when to use this tool (for a full tier list), though it does not explicitly mention when to use compare_products or other siblings.

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 destructiveHint=false, so the read-only nature is covered. The description adds value by disclosing the sort order ('newest research first'), which is not in annotations and helps set correct expectations for the 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?

Two sentences, no filler. The first sentence front-loads the primary functionality and sort behavior, the second sentence provides critical usage guidance. 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?

The tool has an output schema, so return values are documented. With two simple parameters, no nested objects, and clear annotations, the description covers behavior (list, filter, sort) and usage context (prerequisite slug discovery) completely.

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 50% (only query has a description), so the baseline is 3. The description does not add additional parameter details beyond what the schema provides, but the non-parameter context (sort order, usage guidance) compensates marginally.

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 lists categories with published tier lists, newest first. It differentiates itself from siblings by establishing that this tool provides valid category slugs, which are prerequisites for other 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?

Explicitly instructs the agent to 'call this first' when the exact slug is unknown, and explains why slugs cannot be guessed reliably. This provides decisive when-to-use guidance and eliminates ambiguity with sibling 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, destructiveHint=false, and openWorldHint=false, so the agent knows this is a safe, non-destructive, closed-world read operation. The description adds value by revealing that the search is across every board, and that the output is ranked. However, it does not describe pagination behavior, ordering details, or what happens if the query matches many products. For a search tool, this is adequate but not highly transparent 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 a single, dense sentence that conveys purpose, scope, return values, and tool chaining. No word is wasted. 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?

Given the low parameter count (2), high schema coverage for the required parameter, clear annotations (read-only, non-destructive, closed-world), and the existence of an output schema, the description is complete. It explains the search scope (all boards), the returned fields, and how the output connects to sibling tools. The agent has sufficient information to use and chain this tool 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 50% (2/4 properties described—only 'query' has a schema description). The description adds value by explaining that 'name or brand' are the searchable fields, which is more specific than the schema's generic 'Product or brand name' and reinforces the query's scope. It does not add detail about the 'limit' parameter, but the schema already provides a default and bounds. The description compensates for the partial schema coverage by clarifying search 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 specifies a clear verb ('Find') and resource ('ranked products'), and distinguishes the tool by noting it searches by name or brand across every board. It explicitly states what it returns (slug, category, tier) and hints at its role as a prerequisite for 'get_product' and 'get_tier_list', differentiating it from siblings like 'get_product' or 'what_to_avoid'.

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 explains when to use this tool: to find products by name or brand across all boards. It tells the agent that the returned values are what 'get_product' and 'get_tier_list' need next, effectively providing a chaining pattern and an implicit alternative (those tools are for after you have the identifiers). This is explicit 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?

The description adds meaningful behavioral context beyond the annotations: it explains the tool identifies 'bottom tiers' and 'traps' placed by research, clarifying the selection criteria. Annotations already indicate readOnlyHint=true, so no side effects are expected. No contradictions. The description enriches the safety profile with specific data provenance.

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. The first sentence defines the data content, the second tells the agent exactly when to call the tool. Front-loaded with the most critical information. Every word 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?

For a simple tool with one parameter and an output schema (not shown but present), the description adequately explains what the tool returns (bottom tiers, traps) and the intended queries. It does not discuss ordering or pagination, but given the output schema likely handles that, this is sufficient. The description is 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?

Schema coverage is 100% with the single parameter 'category' well-described as a slug. The description does not add new parameter-level details (like format constraints beyond the slug example) but clarifies the role of the parameter in the context of avoidance. Baseline of 3 is appropriate since the schema already fully documents the parameter.

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 defines the tool as returning products in bottom tiers and 'traps' that buyers should avoid. It uses specific verbs ('placed', 'deliberately entered', 'should not buy') and distinguishes from siblings like get_tier_list which would cover all tiers. The resource is the 'what to avoid' list for a category, which is a distinct concept.

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 use cases: answering 'what should I not buy' and checking if a considered product was flagged. It implies when to use (for avoidance questions) but does not explicitly state when not to use or name alternatives among siblings (e.g., get_tier_list for all tiers). This is clear enough for an agent to decide correctly.

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