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

Goes well beyond the annotations: enumerates crawl scope (homepage, four internal pages, robots.txt, sitemap.xml, five competitors), question sampling and source-check rubric, public-research cache reuse with private client data excluded, latency of several minutes, and explicit capability limits (no other MCP connections, no private metrics, no website editing). It also discloses output privacy handling (contact tables, emails, phones omitted), which matches destructiveHint=false.

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?

Purpose and return value are front-loaded, but the middle is a dense multi-clause run-on enumerating every crawl and generation step. The final two sentences ('Returns an audit ID...' / 'Starts the work and returns an id') restate each other, and some detail duplicates schema descriptions.

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 correctly carries the return-value burden (audit ID plus sourced findings, URLs, priorities, drafts, impact, review and measurement steps) and notes latency. It falls short only on not telling the agent that repeated calls create additional stored audits (idempotentHint=false).

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 100%, so all eight parameters are already documented in the schema, including defaults and the 'priority_urls replace automatic page selection' behavior. The description adds only the framing that shared_data snapshots are optional and the audit runs without them, so 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?

Opens with a specific verb and resource: 'Create a stored SEO/AEO audit of a public business website,' and closes with 'Starts the work and returns an id,' which signals the handoff to a retrieval tool. It never names the sibling check_audit, so the distinction from it is inferred rather than stated.

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?

Usage is implied by the behavioral narrative (works without an account or data connection, shared_data is optional). There is no explicit when-not-to-use guidance, no statement of prerequisites, and no warning that this is non-idempotent and a repeat call would start another stored audit.

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