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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds real operational context beyond that: 25k-char paging units, next_offset-based traversal, ~2000-char excerpt windows, accent-insensitive matching, and result capping visible via match_count vs excerpts_returned.

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?

A single front-loaded sentence that leads with the primary purpose (full OCR text) before the excerpt alternative. Dense with parentheticals but each clause carries distinct information; no 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 read-only paging tool with no output schema, the description names the key return signals (next_offset, match_count, excerpts_returned) and both operating modes. It stops short of fully specifying the response envelope, but annotations cover safety and the paging contract is clear.

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?

With schema coverage at 60%, the description compensates well: it explains offset as following the previous part's next_offset, that keyword matching is accent-insensitive, and that excerpt/context output is capped. It adds meaning beyond the terse schema entries, though it doesn't tie every parameter to its behavior.

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 resource (a publication's full OCR text) and distinguishes two retrieval modes: paged full text versus keyword excerpts. An agent knows exactly what it gets, though it does not name or contrast against siblings like search_publications or get_document.

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?

The 'or' construction implicitly tells the agent it can either page the whole document or pull keyword-context excerpts, and the next_offset reference implies chained paging. However, there is no explicit when-to-use guidance versus the many sibling search/get tools, so usage must be inferred.

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