memory.search

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

Goes well beyond the readOnlyHint annotation: it discloses AND matching semantics ('Every term must match'), relevance ordering ('best match first'), and result composition ('full entries plus a snippet with the match in «»'). Those are behavioral traits an agent could not infer from the annotations or schema.

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?

Three compact sentences, each carrying a distinct fact (what/how it matches, ordering and result shape, when to use vs context.get). No filler and the capability statement is front-loaded.

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 read-only search tool with no output schema, the description supplies match semantics, ranking, and return format, which is everything needed to call it correctly. The remaining parameter (limit) is fully covered by the schema.

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 both parameters are already documented and a 3 would be the floor. The description still adds meaning the schema lacks: the conjunction semantics of the query string and the stemming behavior, which affect how queries must be phrased.

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 ('Full-text search ... over the project's long-term knowledge') plus implementation and scope ('SQLite FTS5, stemmed', 'across all sessions'). An agent can distinguish it from memory.get (single entry), memory.put, and context.get without opening any schema.

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?

Explicitly says when to call it ('Use it before solving something that may already be known') and names the nearest alternative with its difference ('context.get already injects a few entries related to the current task'). That is a when-to-use plus a routing rule against a sibling.

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