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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description focuses on adding new information: the empty-query behavior, the 1-50 limit, the per-hit return shape with a next-tool hint, and an explicit prompt-injection warning that hit text is untrusted and must never be treated as instructions.

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 purpose, then arguments, then return shape, then the safety caveat — four dense sentences with no filler. The argument list is compact yet complete.

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, but the description compensates by describing the return entry (kind, id, timestamp, next tool + id). Combined with the injection warning and parameter semantics, an agent has everything needed to search and continue the workflow.

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 and does so: query's omission/empty semantics, kinds as a subset of the three enums, limit's range and default, and projectId's scoping role are all spelled out.

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) plus the exact resource set (one project's reports, error groups and tickets) and the match surface (title/message text). This clearly separates it from the sibling get_* tools, which fetch a single item by id.

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?

It gives the condition that selects this tool (finding items by text) and, crucially, the empty-query fallback behavior (returns most recent instead of everything). It also routes onward by naming the follow-up tool for each hit kind, so the agent knows what to do after searching.

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