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

Beyond the annotations, it discloses that the call is deliberately cheap, that it does NOT return the full 295-check list, what it does return (module why-lines + deduped suggested_tool_call_order), and warns that BI inputs must come from a client conversation. It also flags internal vocabulary that must never surface in the client report. Annotations (readOnly/openWorld/idempotent=false) are not contradicted by the description.

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 is front-loaded in the first clause, and the dense paragraph is justified by the tool's complexity (returns, downstream routing, vocabulary warning). It runs long with many parenthetical asides, which slightly hurts scanability, but each sentence carries distinct guidance.

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?

For a complex, output-schema-less planning tool, the description fully covers what it returns, what it withholds, the follow-up tools, and the client-facing constraint. Annotations plus description leave no critical gap for correct invocation.

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 already 100%, but the description adds real meaning: tier selects the module set (core/deep/autonomous), profile overrides the inferred P1-P4 tier, and site_id triggers profile inference from a real crawl rather than guessing. That goes beyond the schema's terse enum-ish notes.

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 states a specific verb (plan), a specific resource (Five-Layer Search Audit action plan), and its scope (tier module set, why-lines, tool call order) in one call. It explicitly distinguishes itself from get_audit_framework and start_prospect_audit, so an agent can route correctly without opening schemas.

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?

It names when to use this tool (starting point for a Pro SEO Audit), when to use alternatives (get_audit_framework for one module's checklist or the 17-part deliverable), and even points to the search_audit PROMPT over calling cold. It also routes unconnected domains to start_prospect_audit. Nothing is left to inference.

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