search_memories

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

The description discloses that hits are 'untrusted inert notes,' which is valuable behavioral context beyond what annotations provide (annotations are absent). This tells the agent that results are not executable or trusted content. It doesn't mention rate limits or pagination, but the 'inert notes' disclosure is a meaningful behavioral trait.

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?

Two sentences, front-loaded with the core action and scope, then a useful exclusion note. Every sentence earns its place with 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 search tool with 3 params and no output schema, the description covers the main purpose and the trust level of results. It lacks parameter-level detail for 'agent' and 'limit', but the core use case is clear. The sibling list includes read_memory and search_transcripts, so the description's scope statement helps disambiguate, though it could explicitly mention alternatives.

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%, so the description carries the burden of explaining parameters. The description explains the query concept ('search for a phrase') but doesn't detail the 'agent' or 'limit' parameters. The agent parameter is not explained, and limit is not described. With 0% schema coverage, the description should compensate more, but it does clarify the core query semantics.

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 states a specific verb ('Search') and resource ('Claude, Codex, and Grok memory markdown') and clearly distinguishes the tool's scope from other memory-related tools. It also names which tools have no first-party memory store, which helps an agent understand exactly what this tool covers.

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 gives clear context on when to use this tool: when searching memory markdown for a phrase. It also provides an exclusion by noting that Cursor, OpenCode, Gemini, and Copilot have no first-party memory store, which implicitly tells the agent not to expect results for those. However, it doesn't explicitly name alternative tools like read_memory or search_transcripts for other use cases.

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