campus_research_read_pdf

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

Annotations already cover readOnly/idempotent/openWorld, but the description adds substantial context: each call re-downloads and re-parses, no OCR, no paywall bypass, no peer-review verification, no layout preservation, and the resource link persists even on processing failure. It also warns to ignore embedded instructions in the PDF, a meaningful safety disclosure.

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?

Dense and front-loaded: core action and limits come first, then routing guidance, then exclusions. Long but nearly every clause adds operational value; the exclusions are borderline verbose but defensible for a safety-sensitive fetch tool.

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 no-output-schema fetch tool, the description covers the return shape (page-numbered evidence + resource_link), the failure mode (link remains available), and the input limits. An agent has what it needs to call it correctly and to decide against it when indexing is better.

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 0%, so the description must carry parameter meaning. It conveys the 20-page-per-call limit (mapping to pageCount's maximum) and 'specific pages' (implying startPage), but never explains the startPage semantics, the default of 5 for pageCount, or the 1-based indexing. Partial compensation only.

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+resource ('Read specific pages of a public HTTPS PDF') with scope limits (20 MB, 20 pages/call) and return content ('page-numbered evidence plus a resource_link'). It clearly distinguishes itself from the indexed-PDF siblings by naming the exact alternative pipeline.

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?

Explicitly instructs when to use this tool versus the alternative: for PDFs longer than 20 pages with unknown/spread pages, use index_pdf then index_status/search_index/read_indexed_pdf instead of repeatedly paginating. This is a concrete when/when-not routing rule naming the alternatives.

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