search_memory

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

Annotations already declare it read-only and non-destructive, and the description goes further by disclosing the BM25 fallback path, diagnostic mode fields, and that scores are ranks rather than truth probabilities. The note that source text remains untrusted is genuinely useful behavioral context an agent would not get from structured fields.

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?

Four short sentences, each doing distinct work, with the core action front-loaded. The telegraphic phrasing ("bounded source snippets") is slightly opaque and costs a bit of clarity, but there is no filler.

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 with no output schema, the description covers the safety profile and result-scoring caveats but omits any sense of the returned hit structure, pagination via limit, or source_id scoping. An agent could call it, but would be guessing at scoping and result shape.

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% across four parameters, so the description carries the full burden. It only indirectly gestures at the mode parameter (semantic/hybrid vs BM25) and says nothing about query, limit, or source_id, leaving most parameters defined by bare type and default alone.

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 ("Search bounded source snippets"), which tells an agent this is a retrieval operation over stored text. It does not, however, distinguish itself from nearby tools like get_facts or get_evidence_bundle, so an agent still has to infer why it would pick this one.

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 only conditional guidance is around modes: semantic/hybrid requires explicitly enabled local embeddings, otherwise it falls back to BM25. There is no statement of when to use this tool versus its siblings, and no exclusions or prerequisites for the required query parameter.

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