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

Annotations already declare readOnlyHint=true (though destructiveHint=true is oddly noisy for a reference fetch), so the safety bar is lower. The description goes well beyond the annotations by disclosing context-bloat risk, the memory-compression failure mode that dropped the Roadmap tab, the freshness requirement for report_template, and a strong 'never let module IDs/tier names appear in the client output' constraint. It does not describe response format, but with annotations present this is rich added context.

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?

Front-loaded with the core purpose and the AFTER-plan_search_audit ordering, then sections, then the critical report_template warning. It is dense and long, with a narrative aside about the dropped Roadmap tab, but the length is largely justified by genuinely critical behavioral constraints rather than filler.

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 reference-fetch tool with no output schema and fully documented parameters, the description covers purpose, ordering, section semantics, freshness discipline, and an output-usage constraint (no internal IDs in client reports). The only gap is the lack of any indication of return size/shape per section, which matters given the explicit context-bloat warning.

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%, so the baseline is 3, but the description earns an extra point by explaining what each section actually returns ('module' takes a module_id like G2 for one module's checklist; 'deliverable' is the 17-part report structure plus formulas; 'modules' is a filtered list; 'overview' is the small default) and when tier/profile apply. That is meaning the schema alone does not convey.

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 ('full reference detail for one section of the Five-Layer Search Audit framework') and explicitly positions itself relative to the sibling plan_search_audit ('call this AFTER plan_search_audit'). An agent can tell apart what this returns versus what plan_search_audit returns without opening either schema.

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 when-to-use ('for the piece you actually need next'), when-not ('not as a first move', because 26 modules / 295 checks will bloat context), the alternative for a specific domain ('modules' — prefer the plan_search_audit shape), and even a mandatory rule ('call report_template EVERY TIME right before you write a polished report, no exceptions'). This is unusually complete routing guidance.

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