search

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

With no annotations, the description carries the burden of behavioral disclosure. It does explain what fields are searched and what the response includes (URI plus preview fields), which is useful. However, it omits any behavior around result limits, ordering, case sensitivity, or whether the search is read-only, leaving gaps that annotations might otherwise cover.

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 three sentences, each providing distinct value: when to use, what it searches, and what it returns. It is front-loaded with the most important usage condition and contains no unnecessary words.

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 no output schema and no annotations, the description covers the core purpose, search scope, and return preview. However, the namespace parameter is left undefined, and there is no mention of result size, ordering, or pagination, which an agent might need to know for a complete invocation 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?

The description clarifies that query is a keyword for searching, but it does not explain the required namespace parameter at all. The schema only describes query, so with 50% coverage, the description should compensate for namespace but fails to do so. This is a notable gap for an agent deciding how to invoke the tool.

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 that search is the main entry when the URI is unknown, and it specifies the verb (Search), resource (active memories), and the fields searched (uri, content, disclosure, tags, source). This distinguishes it from sibling tools like read and list, which are implied to be used when the URI is known.

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 explicitly says 'Main entry when URI is unknown,' which tells the agent when to use this tool. It implies that other tools like read or list are for known URIs, but it does not explicitly name alternatives or state when not to use search. The condition is clear but not fully expanded.

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