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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. Beyond that, the description adds genuinely useful context: the scope limit ("fix a cluster, not one case") and the intended next-step tool chain, which tells the agent this is an analysis entry point rather than a fixer.

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 usage, then next steps, then limits and an example — no filler sentences. The telegraphic fragments ("Limits: fix a cluster, not one case.") are efficient but slightly clipped, costing a bit of readability.

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 single-parameter, read-only status tool with no output schema, the description covers what is read, when to call it, what to do next, and the granularity limit. It stops short of describing the shape of the returned triggers/clusters, which matters somewhat since no output schema exists.

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?

With only one parameter at 0% schema description coverage, the description must carry the burden, and it does partially by supplying a concrete example value ({"workflowId":"invoice-flow"}) that shows the expected identifier shape. It does not say where to obtain a valid workflowId (e.g., workflow_list), which is the remaining gap.

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 ("Read") and a concrete set of resources ("quality triggers, failure clusters, and open improvement work"), which is enough for an agent to know it is a diagnostic/status read. It also implicitly separates itself from mutation siblings by declaring that it is not the tool for starting a change.

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 when-to-use ("find what to improve") and when-not ("need to start a change"), plus a follow-on chain (skill_list, then workflow_apply_edits). The gap is that the alternative for "starting a change" is never named (improvement_request is the obvious sibling), leaving that routing step to inference.

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