search_memory

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

Annotations already declare readOnly, idempotent, and non-destructive, but the description adds valuable behavioral details: local disk read, no embedding call, no cost, excludes archived/trashed files, and returns [] instead of an error. These go beyond the structured annotations and help the agent predict runtime behavior accurately.

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 dense with information but every sentence serves a purpose. It is front-loaded with the core purpose ('READ-ONLY: lexical search...') and logically flows through scope, exclusions, return behavior, parameter details, and return format. No wasted words for a tool this nuanced.

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 the tool's complexity (3 params, output schema, multiple siblings), the description is fully self-contained. It covers purpose, filtering, empty-result semantics, sibling distinctions, parameter interpretation, return object fields, and the next step (read_memory). Nothing important is left to inference.

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 coverage is 100% with descriptions for all three parameters, and the description enriches each: query is natural-language text, limit has default 8 and cap 50, project_path explains the machine-wide vs project-pinned behavior. This adds meaningful semantics beyond the raw 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 performs 'lexical search over the curated memory tree' and specifies what that includes (decisions, constraints, conventions). It explicitly differentiates from siblings by noting it is 'Not the same store as search_evidence' and directs to ask_memory for a combined store, making the purpose unambiguous.

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?

Provides explicit usage guidance: when to use this tool (lexical search over curated memory), when not to use it (search_evidence for raw files), and the alternative for both plus policy (ask_memory). Also explains the 'returns []' behavior, giving clear context for interpreting results.

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