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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: the weekly-finalization lag, the cost implication (FREE, no AI credits), and the fact it reads stored/connected data. No contradiction with the annotations. Minor gap: it doesn't disclose that different actions return different output shapes, but the output schema absorbs that.

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 dense but efficient: the analysis list is front-loaded, followed by scoping, sibling routing, and cost. Every sentence earns its place, and the cost/staleness notes would be missed if omitted. It is longer than the calibration minimal, but for a six-action dispatch tool the length is justified.

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?

Given a moderate-complexity dispatch tool with six actions, rich annotations, 100% schema coverage, and a present output schema, the description covers the essentials: what it computes, data freshness, scoping, cost, and the sibling to use for raw metrics. Nothing an agent needs to invoke it correctly is missing. A 5 would require even more nuance (e.g., per-action output variance highlighted in prose).

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 coverage is 100% and each parameter (action, days, brandTerms, user_intent, minImpressions) already carries a rich description, including per-action behavior inside the action enum values. The description adds little per-parameter detail beyond schema; its scoping note ('no domain or site parameter is needed') is useful but marginal. Baseline of 3 for full schema coverage is appropriate.

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 names a specific resource (captured Search Console history) and enumerates all six derived analysis types (cannibalization, brand_split, CTR outliers, search_appearance, seasonality, sitemaps). It explicitly distinguishes itself from the sibling gsc_performance: 'Use gsc_performance for raw metrics; use this for the diagnosis layer.' An agent can tell exactly what this tool produces and how it differs from its neighbors.

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 alternative and selection condition ('Use gsc_performance for raw metrics; use this for the diagnosis layer'), which doubles as a when-not. It also flags the data-lag constraint ('finalized weekly... lag live Google by a few days') that should steer an agent away from using it when live data is required, and clarifies scoping so the agent knows no site/domain parameter is needed.

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