search

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

Annotations only declare readOnlyHint=true, and the description adds genuine behavioral context beyond that: every result's scope is marked in the output, and cross-project searches trigger a recorded audit event. That audit disclosure is the kind of side-effect an agent should know before passing cross_project=True. It does not cover result-count behavior or latency/limits.

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 tight sentences with the primary capability front-loaded and the non-default flag constraint immediately after. No filler, nothing to trim.

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?

An output schema exists, so return-value explanation is rightly omitted, and the description covers the one dangerous parameter plus result scope marking. The unexplained k parameter is the only remaining gap for an agent to call this confidently.

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 must carry parameter meaning. It explains cross_project well (intent requirement, scope marking, audit consequence) and query is self-evident, but k (default 5) is never explained in either place, leaving one of three parameters opaque.

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?

States a specific verb (Search) and scopes the resources precisely: current-project notes plus global/shared memory. It cleanly separates itself from other retrieval siblings by scope, though it never names an alternative like dialog_search or search_via_parent, so it falls short of the 5 bar for explicit sibling differentiation.

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?

Gives a real conditional: set cross_project=True only for intentional cross-project recall, which implies a default when-not behavior. It does not name competing retrieval tools or state when a different tool should be preferred, so it stops short of explicit alternatives.

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