Search

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses that matching spans names, frontmatter and content, but says nothing about ranking, result ordering, or how the default limit of 10 behaves.

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 well-formed sentence with the resource and search scope front-loaded and no filler. It is efficient, though it has no structure to speak of beyond the one clause.

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 described. However, with 25% parameter coverage and no usage routing, an agent is left guessing about the tag/limit filters and when this tool beats its siblings.

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 25%: `type` is documented in the schema, while `tag`, `limit`, and `query` are bare. The description does not compensate by explaining tag syntax, whether tag/type combine with the query, or the limit's effect on results.

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 (search) and resource (notes) plus the fields scanned (names, frontmatter, content), so the agent knows exactly what is being matched. It does not differentiate itself from siblings like `read` or `context`, which is the only thing keeping it from a 5.

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 guidance on when to choose `search` over `read`, `context`, or `people_graph`, nor any stated preconditions. The keyword-search framing implies a full-text lookup, but the agent must infer that itself.

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