Recommend kits for a project

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

With no annotations provided, the description carries the full burden. It discloses that the tool requires an API key, costs 3 quota units, returns meta.depth and meta.order to clarify mode and ordering, returns 400 if context is missing, and explicitly says 'Creates nothing' to signal no side effects. This far exceeds the transparency normally expected.

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 paragraph but each sentence adds distinct value: purpose, candidate contents, ranking mode, differences from other routes, and prerequisite. It is front-loaded with the core function and avoids fluff, though it is somewhat dense in presentation.

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?

Even without an output schema, the description explains what the response contains (candidate self-cases, meta.depth, meta.order), the auth and quota conditions, the error scenario, and the read-only nature. For a tool with two parameters and no output schema, this fully equips the agent to select and invoke it 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 100%, so baseline is 3. The description adds contextual meaning to projectId by tying it to set_project_context and stored context, and clarifies that limit only controls candidate count. While limit is self-explanatory, projectId's prerequisite is well articulated, adding value 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 the tool recommends kit candidates for a specific product, grounded in stored project context. It distinguishes from siblings by emphasizing that it uses stored context instead of a re-sent description, and explicitly differentiates from list_themes and search_themes by cost and auth requirements, plus 'Creates nothing' clarifies side-effect-free behavior.

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 explicitly says 'Call set_project_context first' as a prerequisite and notes that a project without stored context returns 400. It also highlights the two differences from other discovery routes: higher quota cost and API key requirement, and explains the two modes (free candidates vs. ranked with Pro+key), which gives clear when-to-use and alternative comparisons.

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