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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is free; the description instead spends its budget on behavior the agent could not otherwise know — lenient Arabic matching ('قصه' finds 'قصة', '٥' finds '5') so no manual spelling variants are needed, and that results are short summaries requiring a follow-up get-* call. That is exactly the value-add expected alongside annotations.

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-loaded with the core verb and scope, then routing rule, then matching behavior, then return-value guidance, then exclusions — a sensible priority order. Slightly long, and the opening kind-enumeration is both partial and redundant with the `types` parameter, which costs a point.

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?

Complete for a search tool: what it covers, what it excludes, how matching behaves, what comes back (summaries) and which sibling to call next. With no output schema, the sentence about short summaries and follow-up get-* calls is precisely the missing piece an agent would otherwise have to guess.

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 the baseline is 3; the description rises above it by telling the agent how to form the required `query` (lenient normalization, no need to try variants) and by stating that the matched fields are titles and bodies. It adds nothing about `limit`, `cursor` or `project_id`, but those are fully documented in the schema.

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 scope ('Search across everything the signed-in user has ... projects, scripts, the sections inside scripts, and ideas') and explicitly contrasts itself with the list tools. The only weakness is that its enumeration of searchable kinds is incomplete — the schema's `types` parameter also lists content series, scheduled items, storyboards, filming locations, equipment, shoot days and thumbnail briefs, so an agent reading only the description would under-estimate coverage.

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 an explicit rule for choosing this over siblings ('Prefer this over the list tools whenever you are looking for something specific rather than browsing — the list tools page through everything, this matches text') plus explicit exclusions ('Does not search tasks, habits, personal subscriptions, or anything about billing'). Both the when and the when-not are covered.

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