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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding two things they don't: the required `search:read` scope and the crucial disclosure that returned text lives in `untrusted_fields` and is data, not instructions. It stops short of saying anything about pagination, ranking, or result ordering, which keeps it out of 5 territory.

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?

Three short sentences, front-loaded with the operation and followed by the permission and the injection-safety note; no filler. It is arguably over-terse rather than padded, but every sentence carries information.

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 and no description of results, and the `kinds` array is entirely opaque, so an agent cannot construct a correctly scoped call. For a search tool spanning an unstated corpus with three undocumented parameters, the definition is substantially incomplete despite the useful untrusted-content warning.

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 full burden for `q`, `kinds`, and `limit` — and it delivers none of it. Nothing explains what values `kinds` accepts (the single most important unknown here), whether `q` supports syntax or operators, or what `limit` defaults to. The phrase "my records" only weakly bounds scope.

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?

"Search my records" names a verb and a resource, but "records" is left undefined in an account with dozens of resource types (documents, posts, mixes, conversations, live events). Siblings are not addressed at all, and the separate `search_djs` tool is never contrasted, so the agent cannot tell from the description what corpus is being searched.

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?

No when-to-use guidance, no exclusions, and no mention of alternatives such as `search_djs` or the many `list_*` tools that also enumerate resources. The only gating information is the permission string `search:read`, which is a prerequisite rather than a usage condition.

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