campus_research_read_pdf

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds substantial detail: limits on size/pages, continuation and truncation indicators, explicit non-capabilities, safety fallback (resource link remains available), and security instruction to ignore embedded PDF instructions. This far exceeds the baseline and provides critical behavioral context beyond annotations.

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?

The description is a single, dense paragraph that front-loads the core purpose and then covers limits, non-goals, and safety. Every sentence adds value; there is no fluff or redundancy. It is comprehensive yet succinct.

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 tool with no output schema, this description is exemplary. It covers input constraints (URL, size, pages), processing limits, output format (page-numbered text, resource_link), edge cases (continuation, truncation, safe failure), and security instructions. An agent has everything necessary to call this tool correctly and interpret its results.

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%, so the description must compensate. The description explains the overall behavior (page-numbered text, limits) and the tool's purpose, which implies parameters like startPage and pageCount. However, it does not explicitly explain each parameter (e.g., how startPage and pageCount interact, what pageCount default means). This is a moderate gap given zero schema coverage, but the description is thorough enough to infer usage.

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 starts with a specific verb ('Read') and resource ('accessible public HTTPS academic PDF'), clearly stating the output is 'page-numbered text evidence' and 'resource_link'. Even with sibling tools like campus_research_read_document and campus_research_verify_evidence, this tool's purpose is distinct and 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?

It clearly states constraints (public HTTPS, max 20 MB and 20 pages) and exclusions (does not bypass paywalls, perform OCR, verify peer review). It doesn't explicitly name alternative tools, but the context makes it obvious when to use this tool versus a verification or search tool. Could benefit from explicitly saying 'use this for reading, not for verification'.

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