memory_search

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

No annotations are provided, so the description carries the full burden. It states the tool 'searches' which implies a read-only operation, but does not explicitly disclose that it makes no modifications. It also does not mention performance characteristics (e.g., indexing), result ordering, or any potential side effects like caching. This is acceptable for a search, but the absence of explicit read-only confirmation or other behavioral notes leaves a minor gap.

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 concise and well-structured. It starts with a one-sentence purpose statement, then lists parameters in a bulleted format with clear labels. There is no redundant fluff, and the most important information (the search behavior) is front-loaded. Every sentence contributes value, and the parameter descriptions are directly actionable.

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 that an output schema exists, the description need not explain return values. It covers the tool's purpose, all parameters with semantics, and minimal usage context. However, it falls short on usage guidance relative to siblings (e.g., when to use this over memory_retrieve) and does not mention any edge cases or limitations (e.g., whether searches are case-insensitive, or how tags/namespace interact). These omissions are minor, but they prevent a perfect score.

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?

The description provides detailed semantic meaning for every parameter, going well beyond the schema (which has 0% description coverage). For example, project_root is specified as 'absolute path to active project root directory', query is described as 'search string across keys, frontmatter, and content', and limit is given a default meaning. This fully compensates for the lack of schema descriptions and enables correct usage without ambiguity.

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 opens with a clear verb 'Searches' and a specific resource 'persistent memories', and enumerates matching criteria (keywords, tags, namespace patterns). This is distinguishable from siblings like memory_retrieve (which likely fetches a specific memory) and memory_store (which writes), so an agent can tell them apart at a glance.

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 explains what the tool does and its parameters, but does not explicitly state when to prefer it over sibling tools like memory_retrieve or memory_get_last. The intended use case (searching rather than retrieving) is implied by the word 'Searches' but not spelled out. It lacks explicit 'when not to use' guidance, such as 'use memory_retrieve for exact ID lookups'.

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