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

Annotations only declare the safe read profile; the description adds real behavioral context — conjunction matching (every word must appear), permission-scoped results ('Only files on pages you may read'), and the exact shape of a hit (file id/name, wiki page, PDF page, snippet). It omits ranking/ordering behavior, which keeps it short of a 5.

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?

Four tight sentences, front-loaded with what is searched and what each hit returns, then the permission caveat, then sibling routing. Minor awkwardness in 'the pages of articles read with formulas (read_pdf_text)' but nothing is wasted.

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 three-parameter search with no output schema, the description covers the corpus, matching semantics, result fields, and access constraints — everything an agent needs to decide to call it and interpret the response. The absence of an output schema is compensated by the inline hit description.

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 100%, so the schema already documents query, limit and project. The description adds meaning to query by defining AND semantics and allowing TeX fragments, but says nothing extra about limit or project scoping beyond what the schema states — baseline 3.

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 — finding PDF pages that contain all the queried words — and ties the corpus explicitly to articles previously processed by read_pdf_text. The TeX-fragment example ('\pi_{n+k}') and the per-hit fields make the scope unambiguous, and it distinguishes itself from sibling search tools.

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?

Clearly implies the corpus is limited to PDFs already ingested via read_pdf_text, and routes other content types to find_issues / search_wiki. It does not spell out a negative case (e.g. use read_pdf_text when you want full page text rather than matching), but the alternative routing is explicit enough.

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