Recall

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

With no annotations provided, the description carries the full burden. It discloses the ranking formula (text * trust * state * (1 + freshness + heat)) and notes that old unused memories sink but never vanish, revealing decay behavior. It also states 'nothing is auto-injected,' implying no side effects on memory content, which adds transparency about its read-only nature.

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 concise and front-loaded, opening with the core search functionality before explaining the ranking details. The two sentences are dense but purposeful, though the ranking formula might be clearer if separated, and no unnecessary words are present.

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?

Given 7 parameters, no output schema, and no annotations, the description is insufficient for an agent to fully understand how to use all parameters. It explains the return type and ranking but omits details on filters like types, include_archived, and include_deprecated, and does not describe output fields or pagination. This is a notable gap for a complex search tool.

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 43%, leaving limit, types, include_archived, and include_deprecated undocumented in the schema. The tool description does not clarify these parameters, nor does it explain how the ranking formula maps to specific inputs like entities or types. It adds some context about ranking but fails to compensate for the low coverage.

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 performs a hybrid lexical search (word/trigram FTS + CJK-aware fallbacks) and explicitly mentions it returns paths, excerpts, and score components. It differentiates itself from memory_read by noting that full content must be read via that tool, and from other siblings by focusing on search rather than writing or management.

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 provides clear guidance to use memory_read for full content, implying this tool returns only excerpts and paths, and that nothing is auto-injected. It does not explicitly mention when not to use it versus other siblings like memory_reindex or memory_status, but the contrast with memory_read is a useful usage signal.

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