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

Annotations already declare readOnlyHint/idempotentHint/no-destruction, so the safety profile is covered. The description adds genuinely useful behavior beyond that: which layers are searched (`content`, `forms`, `annotations`) and that results are paginated via a returned `next_cursor` fed back as `cursor`. It does not mention handling of encrypted/password-protected documents even though a `password` parameter exists.

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?

Three compact clauses: purpose and return shape first, then filtering and pagination, then the workflow recommendation — a sensible front-loaded order with no filler sentences. The heavy parenthetical nesting (match modes, layer list) makes it dense rather than elegant, 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?

With no output schema, the description correctly takes on the burden of describing the return value (spans with page/position/font/span id) and the pagination contract, and it names the layers searched. For a read-only tool with annotated safety this is nearly complete; the only real omission is behavior for password-protected PDFs and any hint about the `limit` default.

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 low (25%), so the description has to carry weight and largely does: it explains that `query` uses "the same four `match` modes an edit uses," that `pages` scopes the range, that `layers` selects among content/forms/annotations, and how `cursor`/`next_cursor` interlock. It leaves `limit` and `password` unaddressed, so it is not fully compensating, but the coverage of the semantically demanding parameters is strong.

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 states a specific verb and resource ("Read the text of a PDF") and immediately enumerates what is returned: every span with its page, position, font and span id. It also distinguishes itself from siblings by positioning itself as the read/inspection step that precedes `pdf_edit`, so an agent can tell it apart from pdf_edit, pdf_preview and pdf_batch without opening schemas.

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 gives an explicit use case and sequencing: "Use it before `pdf_edit` to check what a document actually says and to pick the `scope` that selects the match you mean." That is clear when-to-use guidance anchored to a named sibling. It stops short of explicit when-not guidance (e.g. when to prefer `pdf_preview` for rendered pages or `pdf_batch` for multiple files), which keeps it below a 5.

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