campus_research_audit_indexed_pdf

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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing semantic caveats: no_extractable_text is not proof of a blank page or OCR failure, and visualReviewRecommended is a lead rather than visual inspection. It also scopes what the tool cannot certify, which is exactly the kind of behavioral context annotations don't carry.

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-loads the purpose, then layers caveats that each carry real decision value. It is somewhat dense but no sentence is filler given the interpretability warnings.

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 does a good job explaining how to interpret the manifest's signals and what the tool cannot prove, which is critical for an audit tool. The gap is parameter explanation and any indication of the manifest's structure, but for interpretation guidance it is largely complete.

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% across three parameters (analysisId, documentId, includePages). The description only hints that the PDF must be 'prepared' but never explains what analysisId, documentId, or includePages mean or their defaults, so it fails to compensate for the missing schema documentation.

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 ('Create a page-by-page audit manifest for a prepared PDF') and enumerates what it classifies (extracted text, truncation, figure/table/box signals), making it distinguishable from read/index siblings. It does not name an alternative explicitly, but the scope is unambiguous.

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 workflow guidance ('Use the original PDF resource link to inspect flagged pages, then state exactly which pages were inspected') and states limits ('cannot certify whole-document critical reading'), but never says when to prefer this over campus_research_index_pdf, index_status, or read_indexed_pdf. Usage is implied rather than routed.

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