search_witness_memory

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds context about returning sanitized previews and evidence hashes (not raw payloads), and states it's free, which aligns with annotations and provides useful behavioral insight beyond 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?

The description is a single concise sentence that front-loads the main action. The word 'Free' is slightly extraneous but not detrimental. It is appropriately sized.

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?

With 8 parameters and no output schema, the description is minimal. It does not clarify how parameters interact (e.g., whether query can be combined with agent_id), nor does it mention pagination, ordering, or error handling. The description leaves significant gaps for an agent to use 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 100%, so baseline is 3. The description lists the same searchable fields as the schema but does not add deeper meaning or usage nuances for parameters. No additional semantics beyond the 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 description clearly states the tool searches continuity-safe witness memory by query, session_id, agent_id, or ontology layer, and specifies it returns sanitized previews with evidence hashes. This distinguishes it from sibling tools like get_witness_lineage or peer_witness by emphasizing safety and privacy.

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 lists searchable fields but provides no explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or when not to use it.

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