discover

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

Annotations declare readOnlyHint=false, so the description's 'Writes only Capalith's catalog, never sources or host settings' is essential and non-obvious context explaining the write. It also states it 'does not load or activate skills,' bounding side effects, and explains snapshot vs. refresh semantics.

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?

Front-loaded with purpose, then state/side-effect constraints in compact sentences. It is dense and mostly earns its space, with minor redundancy between the snapshot and refresh sentences.

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?

An output schema exists, so return values need not be explained, and the description covers the stateful behaviors (catalog preparation, snapshot reuse, refresh) an agent must know. It is complete for a 9-parameter search tool, though pagination semantics could be slightly clearer.

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?

With 100% schema coverage the baseline is 3, and the description adds real meaning beyond the schema: workspace and host_homes select task/profile context when it differs from the server, and extra_source_paths is described as replacing previous additions. view_id pagination usage is only lightly covered, keeping this at 4.

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 Agent Skills by task') and clarifies scope ('including known skills and declared relationships'). It also distinguishes itself from the sibling index_skills by naming it directly, so an agent can route correctly without opening schemas.

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?

Gives clear context: the first search builds the catalog, repeated searches read the snapshot, and index_skills is the explicit refresh path. It lacks an explicit when-not-to-use statement (e.g., versus inspect or traverse), but the index_skills routing is concrete.

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