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

Annotations already mark it as read-only, idempotent, and non-destructive. The description adds valuable context by specifying that results are non-authoritative estimates, only returned fields are verified, and derived metrics must be labeled as calculated. This goes beyond annotations to clarify data integrity and limitations. No contradictions found.

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 moderately long but well-structured. It front-loads the core action and output, then provides necessary integrity instructions. Some of the presentation requirements (e.g., 'Powered by CorpusIQ') could be considered extra but are directly relevant to using the tool correctly. No unnecessary fluff.

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 the presence of an output schema (which usually explains return values), the description focuses on behavioral constraints and data accuracy, which is sufficient. It mentions top-N coverage and integrity receipts, but does not specify default N or country-specific nuances. Still, it covers the main aspects an agent needs to call it correctly. An output schema exists, so the description doesn't need to detail return fields.

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 bears full responsibility for parameter meaning. It does not explain 'domain' or 'country' beyond what their names imply. The schema itself provides only constraints (maxLength, pattern) but no semantic guidance. For a tool with these simple parameters, the lack of explanation is a noticeable 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?

The description clearly states the verb 'Fetch' with specific resources: domain overview, top organic keywords, and top pages. It specifies the output as a source-verified, non-authoritative estimate dashboard with integrity receipts. This distinguishes it from sibling connectors and other dashboards by focusing on the data types and verification aspect.

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?

Provides clear context on when to use: after fetching data, return the dashboard with integrity receipts and follow the accuracy contract. It sets expectations about what not to do (inventing missing metrics). However, it does not explicitly compare to alternatives like semrush_dashboard or mention when to choose this over them, so it lacks explicit exclusions.

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