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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description correctly spends its words elsewhere: it discloses the aggregation model and the per-group payload shape, which matters because there is no output schema. It stops short of stating result caps, ordering, or how patterns are clustered.

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?

A single sentence that front-loads the result shape, then appends the alternate mode after a semicolon. No filler, no restatement of the title.

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?

For a 6-parameter, no-required, schema-thin read tool, the description supplies the essentials: what comes back, how it is grouped, and how to drill into one pattern. Remaining gaps (search semantics, default window, result limits) are modest and partly covered by the range parameter's own default note.

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?

At 33% schema coverage the description must compensate, and it does well for the least obvious parameter by explaining that `pattern` is a message-pattern key returning that pattern's latest lines. But `search` (the ambiguous one — message text? pattern text?) and `level` are left entirely to the schema, so the compensation is partial.

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 resource (WARN/ERROR log lines from the app), a specific transformation (grouped by message pattern), and the fields exposed per group (count, last seen, code location, example traces). An agent can tell this is the aggregated log-view tool rather than a raw trace or metric tool, though no sibling (e.g. relia_trace) is named to sharpen the contrast.

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 two-mode rule: call as-is for grouped patterns, 'pass `pattern` for that pattern's latest lines'. That resolves the main branching decision inside the tool. It does not say when to prefer this over relia_trace or relia_session, so the guidance is contextual rather than exhaustive.

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