Use Which Tool

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and a closed world, so safety is covered. The description adds two real behavioral facts beyond that: results are unranked ("Not ranked") and the tool operates on a batch of 2–4 ids. It says nothing about what the entries contain or how order/unknown ids are handled.

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 very short sentences, front-loaded with the core behavior and immediately qualified by 'Not ranked'. Nothing is padded, though the terseness edges toward under-specification rather than crisp economy.

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?

There is no output schema, so the description should ideally say what a 'side-by-side entry' includes or how mismatched/unknown ids are handled. Given a one-parameter, annotation-covered read tool the omission is tolerable, but an agent still cannot predict the response shape.

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% for the single 'ids' parameter, but the description does name it as a list of tool ids and repeats the 2-to-4 cardinality already enforced by minItems/maxItems. It adds the referent (tool ids) but no format, source of ids, or behavior for invalid/duplicate ids.

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 phrase "Side-by-side entries for 2 to 4 tool ids" conveys comparison of multiple tools, which does distinguish it from get_tool (single id) and search_tools/list_categories. However, it uses a noun phrase rather than a verb+resource statement, so the action performed (returning a comparative view of tool entries) is inferred rather than stated.

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 explicit when-to-use guidance and no named alternative. The '2 to 4 ids' framing implies batch comparison versus the single-id get_tool, but the agent must infer that from sibling names rather than being told 'use get_tool for one id, use this for several'.

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, non-destructive, closed-world behavior, so the description's job is lighter. It adds real value by disclosing what comes back — verdict, use cases, strengths, limitations, and pricing with source and verified date — which is exactly the payload context an agent needs.

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 front-loaded sentence with the resource, the lookup key, and the returned fields; nothing is wasted. The colon-list of fields is dense but readable, the only minor cost being a long sentence.

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 one-parameter read tool with no output schema, the definition covers the lookup key, its format, and the shape of the returned entry. Only the absence of explicit fallback guidance (what happens on an unknown id) keeps it short of full 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 coverage is 0% and the single `id` param has no schema description, so the description must compensate. It does so with two concrete slug examples, making clear the id is a short tool identifier rather than a numeric key; it does not restate the maxLength constraint.

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 ('Full entry for one tool by id') and anchors it with concrete id examples ('cursor', 'claude-code'). It implicitly separates itself from search_tools/compare_tools by being a single-record lookup, though it never names a sibling 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?

The phrase 'by id' implies the caller must already have an id, which hints at using search_tools first, but this is left to inference. There is no explicit when-to-use, when-not-to-use, or named alternative.

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 read-only, idempotent, non-destructive, and closed-world, so the safety profile is fully covered elsewhere and the description is not required to restate it. The description does add one piece of behavioral value beyond annotations: that results are grouped by category with tool ids nested inside each, which hints at the return shape. It says nothing about whether the category set is fixed, ordering, or size.

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?

It is a single short line with no wasted words, but it is a grammatical fragment rather than a front-loaded statement of action, reading as under-specification rather than deliberate economy. A verb at the start would cost nothing and remove the ambiguity.

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 zero-parameter read tool with full annotation coverage and no output schema, most of what an agent needs is present or handled by structured fields. The remaining gap is that the description never says the call returns the full category listing, nor whether it is exhaustive or paginated.

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 takes zero parameters, so there is nothing for the description to clarify beyond what the empty schema already conveys; 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 noun phrase 'Categories in the directory with the tool ids in each' identifies the resource (categories) and hints at the grouping of tool ids, which distinguishes it from the tool-oriented siblings. But there is no verb and no statement of what the tool actually does with them, so an agent must infer that it returns a listing.

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 call this versus compare_tools, get_tool, or search_tools, and no mention that it takes no inputs and is the natural entry point for discovering the directory's taxonomy. The agent gets context only by inference from the sibling names.

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, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results carry verdicts, pricing, an official source URL, and a verification date, plus a citation obligation the agent must honor.

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 what the tool searches, then what it returns, then the citation requirement. No filler and nothing buried.

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 three-parameter lookup with no output schema, the description conveys the source, the return contents, and the attribution requirement. It is close to complete, missing only how many results come back and how category/limit interact with 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?

Schema coverage is only 33%: query has a description and category is a self-describing enum, but limit (1-20) is undocumented in both schema and description. The description says nothing about how query matching works or that category narrows results, so it fails to compensate 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?

States a specific verb and resource: 'Search the Use Which Tool directory of AI tools for builders.' An agent can tell this is a keyword search over a curated directory, though it never explicitly contrasts itself with siblings like get_tool or list_categories.

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?

Usage is implied by the verb 'search' and the target audience ('for builders'), but there is no explicit when-to-use versus when-to-use-a-sibling guidance, and no note that get_tool should follow for full details or that list_categories exists for browsing.

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