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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds non-obvious traits those annotations cannot express: that the call is 'Free', that results are addresses intended for fetch rather than full records, and that an empty query degrades to a recency listing. It stops short of pagination or limit interaction beyond what the schema says.

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?

Front-loads the value proposition and return shape, then layers usage, then the empty-query fallback, with no filler sentences. Length is justified by the number of distinct behaviors it must convey for a general-purpose search.

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?

There is no output schema, so the description carries the return-shape burden and does so ('an address for each hit'), plus cost, zero-arg behavior, and the natural follow-up tool. For a 4-param optional-args search over a large sibling set, nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so all four parameters are documented in the schema already, including the empty-query and kind-omission behaviors. The description restates these ('Leave the words empty', 'Use kind=audit') rather than adding syntax or format detail beyond them, so the baseline of 3 is correct.

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 and resource — finds any work in the workspace by words — and immediately frames the result as 'an address for each hit that you pass straight to `fetch`', which separates it cleanly from the sibling fetch tool and from get_* lookups. An agent knows exactly what this returns and what to do with it.

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 concrete trigger conditions with quoted user phrasings ('the zoomdrain page', 'last month's audit'), states the zero-arg behavior ('Leave the words empty to list the most recent of everything'), and pre-empts a likely detour with 'an account overview is not needed first'. Explicit when-to-use plus a routing rule to kind=audit.

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