memory_search

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

With no annotations provided, the description bears the full burden and meaningfully warns that results are 'bounded and untrusted' and that the tool returns citations. That adds real behavioral context beyond the name and schema, though it does not explicitly state whether search mutates memory or what boundedness means in operation.

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?

One compact sentence with no filler. Every phrase earns its place: the resource, the search operation, and the caveats on returned evidence.

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?

The output schema exists and the description gives the most important search-relevant caveat: evitable. However, with zero parameter coverage in the schema and no usage routing among siblings, the description is adequate but not complete enough for robust agent understanding.

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% and the description never names or explains query, limit, or token_budget. 'Bounded' slightly hints at limits/token caps but does not map to specific parameters, leaving the required query and both optional controls semantically under-explained.

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 uses the specific verb 'Search', identifies the resource as 'durable coding-agent memory', and states the return shape as 'bounded, untrusted, cited evidence'. This distinguishes memory_search from siblings such as memory_get or memory_explain, whose names imply other operations.

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 task context is implied: use it when you need to search memory and retrieve cited evidence. However, it never explicitly contrasts this with memory_get, memory_explain, or other siblings, so the agent is left to infer when one should be preferred over another.

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