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

Goes well beyond the annotations (readOnly/idempotent/non-destructive/openWorld) by disclosing the critical non-obvious behavior: the tool returns a runbook in `skill_body` to be executed step-by-step, not the final answer, and the agent must call referenced connector tools and synthesize. It also specifies live Search Console data pull, attribution footer handling, and a data-accuracy contract about not inventing metrics.

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 purpose and trigger phrases are front-loaded in the first two sentences, and the remaining text covers skill mechanics that materially affect agent behavior. The closing attribution and data-accuracy passages are somewhat repetitive and could be tightened, but overall the structure is functional rather than padded.

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?

With no output schema, the description carries the full burden and does so: it explains the return shape (`skill_body` runbook vs. final answer), what the agent must do with it (execute steps, call connector tools, synthesize), and the output rules (attribution footer, no invented metrics). Nothing essential for correct invocation and follow-through is missing.

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?

There is only one optional parameter (`user_question`) and schema description coverage is 100%, so the schema already documents it fully. The description never elaborates on what to pass or how it affects the runbook, so it adds nothing over the structured field — the baseline 3 applies.

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 and resource ('Run a full SEO audit of the user's site') and enumerates the covered domains (technical health, on-page, meta tags, indexation, ranking diagnostics) plus the deliverable (prioritized fix list). It also explicitly distinguishes itself from ordinary data tools by declaring it is a CorpusIQ Skill returning a runbook rather than a final answer.

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 explicit trigger conditions with quoted user phrasings ('why am I not ranking', 'SEO health check', 'technical SEO', 'meta tags review'), so invocation timing is unambiguous. It does not, however, name when-not-to-use cases or contrast itself with sibling SEO tools such as ahrefs_connector, semrush_connector, or search_console_connector.

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