recall

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

With no annotations provided, the description carries the full burden, and it delivers: result ranking, project bias, the "via" receipt, excerpt behavior with truncated/body_chars, deterministic newest-first listing for tag-only queries, staleness guidance via updated_at, and full/complete-body modes. This is unusually transparent about how the tool behaves beyond its inputs.

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 front-loaded with the core purpose and then organized into usage, return-shape, and Args sections. It is longer than average, but the length is justified by missing schema descriptions. There is minor redundancy between the prose explanation of id/full and the Args block, so it is not maximally lean, but every section earns its place.

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 an 8-parameter tool with no annotations, no output schema, and no schema descriptions, this is remarkably complete. It explains all parameters, the shape of each hit, what truncated means, how to fetch full bodies, staleness handling, and how to use tags versus query. An agent has everything needed to select and invoke the tool correctly.

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 0%, but the description's Args section documents all 8 parameters with meaningful behavior: query is free text and optional with tags; type filter values; limit default; budget controls association depth; session groups recalls; tags are exact-match and can be used alone; id fetches one full memory; full returns complete bodies and notes the payload cost. This fully compensates for the empty schema.

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 first sentence states a specific verb and resource: "Search memories by keyword and semantic similarity, then follow the usage graph to related memories, most relevant first." It also covers the secondary fetch mode via recall(id=N), and the role as the read/search tool is clearly distinct from sibling tools remember, link, and forget.

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?

The description gives strong timing guidance: "Recall BEFORE starting a task, not only when stuck" and explains why (the session index is titles only). It also gives clear internal alternatives such as "To read one in full, call recall(id=N)" and "prefer id= for the one memory you actually need." It does not explicitly state when to choose remember/link/forget over recall, only mentioning them as update targets, so some sibling routing is left implicit.

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