guide.search

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

The description explicitly states 'reads the bake, never the live farm' and 'a walk is reproducible', indicating no side effects and deterministic behavior. This fully discloses the read-only, non-mutating nature of the operation.

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 two sentences with the main purpose front-loaded. However, it includes several idiosyncratic terms (baked fedwiki, lattice vertex, PSI element) that add length and may obscure meaning, though they are likely domain-specific for this toolset.

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?

It describes the output structure (each step with site, slug, lattice vertex, PSI element) and the two-stage algorithm, giving the agent enough context to understand the result format. It does not cover edge cases or error behavior, but this is acceptable for the given 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 description coverage is only 33% (sites has a description, but query and limit do not). The tool description does not explain the meaning or expected format of any parameters, leaving parameter semantics under-specified.

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 searches the guide and returns an ordered walk of pages, mentioning the data source (baked fedwiki federation), algorithm (BM25 + link-graph expansion), and output elements. This distinguishes it from page-level tools, though some jargon may reduce immediate clarity for a general agent.

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 implies a static snapshot ('reads the bake, never the live farm') and emphasizes reproducibility, but does not explicitly contrast with sibling tools like guide_neighbours or guide_page. The when-to-use decision is partially left to inference.

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