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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds meaningful behavioral context: live data when read credentials exist, a dashboard fallback note otherwise, and project selection behavior across multiple runtimes and project groups. This goes well beyond the annotations without contradicting them.

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?

The description is front-loaded with the core comparison and regression purpose, then layers in credential behavior and project selection. It is dense but each sentence contributes necessary context. The later sentences are somewhat run-on and could be tightened, so it is not a perfect 5.

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, so the description must carry the burden of explaining the response. It mentions regressed screens, a fallback note, your_projects, project_group, and readings, which gives an agent a reasonable picture of what to expect. It could be more explicit about the exact response shape, but the coverage is solid for a read-only tool with zero required parameters.

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 already 100%, so the baseline is 3. The description adds value by explaining the relationship between account_token and project, how 'name (runtime)' or install id selects among multi-project/multi-runtime accounts, and the fallback when no token is supplied. This semantic context is not fully captured by the parameter descriptions alone.

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?

The description communicates that the tool compares an older auto-learned p95 baseline against recent p95 values and identifies regressed screens. It is specific enough to stand apart from sibling diagnostics like crash_risk or trend, though it never explicitly names an alternative. The phrasing lacks a direct verb like 'compares' or 'reports', so it is clear but not maximally explicit.

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?

The intended use is implied: call this when you need p95 budget regression information. The description provides useful contextual guidance around credentials and project selection, explaining what happens with or without account_token. It does not, however, explicitly say when to prefer this tool over related siblings or when not to use it.

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