recall_server_findings

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

With no annotations, the description carries the full burden and does well: it discloses the return content (titles AND bodies), the default ordering (newest-first), the active-findings default, and a substantive trust model ('agent-authored and unverified ... re-verify before taking any destructive action'). It omits pagination and auth/rate-limit context, keeping it from a 5.

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 mode behavior, then the trust caveat. Every sentence earns its place and the safety-critical warning is given prominent placement.

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 no-annotation, no-output-schema tool, the description covers return content, ordering, defaults, and the trust model adequately. Minor gaps remain around pagination and whether superseded findings appear by default, but the schema handles that flag.

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 100%, so the schema already documents all five parameters including query, tags, limit, and include_superseded. The description largely restates the query semantics already present in the schema, adding only the 'active findings newest-first' framing, so baseline 3 is appropriate.

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 (recall) and resource (previously-saved findings) and clarifies scope ('for an instance'). It distinguishes itself from the write counterpart remember_server_finding by noting it returns 'full titles AND bodies', though it never names list_server_memories, a sibling that could plausibly overlap.

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 explicit mode selection: omit query to list all active findings newest-first, supply query for lexical search. This is clear actionable guidance, but it stops short of contrasting with siblings like list_server_memories or remember_server_finding.

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