cpu_find_buildings

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

With no annotations provided, the description carries the full behavioral burden, and it does so comprehensively: read-only, no session needed, no-match returns a plain answer rather than an error, default limit behavior, and single-match card behavior. It also clarifies the lifecycle distinction between buildInput and recipeInput, which is critical for correct invocation.

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 dense but well-structured: search intent first, parameter semantics second, output shape third, and edge cases last. Every sentence carries operational information, and there is no filler or redundant restating of the tool name.

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 tool with no output schema and no annotations, this description covers invocation semantics, result format, default row count, filtering strategy, edge cases, and session/auth requirements. An agent has enough context to call it correctly across common scenarios.

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?

All seven parameters already have schema descriptions, so the baseline is 3. The description adds value by grouping the four resource filters into distinct roles and explaining the AND-combination semantics, going beyond the per-property schema text. It does not reinvent the parameter details, but it does synthesize them into actionable guidance.

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 opens with a specific verb and search dimension: 'Search the building catalog by what a building consumes, produces or mines', plus an illustrative query. It clearly distinguishes this from the closest sibling, cpu_get_building, by mentioning the single-match full-card behavior. This is far more than a tautology.

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 states filters are optional and AND-combined, that kind and tier narrow results, and advises narrowing filters rather than paging. It references cpu_get_building for the single-match case, implying the boundary, but it does not explicitly say 'use cpu_get_building for exact ID lookups' or list when-not-to-use this tool.

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