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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely new behavioral context: no OCR fallback, SSRF-style refusal of private/local addresses, and the shape of the return (per-page text, headings, token count).

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 short sentences, front-loaded with the core action, then return shape, then input method, then the constraint. Every sentence carries distinct information with no padding.

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?

An output schema exists, so the return description is a bonus rather than a necessity, and the safety profile is in annotations. The only real gap is the two undocumented parameters (filename, mimeType); otherwise an agent has everything needed to call it.

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 50%: url and data are documented in the schema, while filename and mimeType are undocumented in both places. The description reinforces the either/or input choice and repeats the private-address rule, but adds no syntax or format detail beyond the schema.

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 ('Read the selectable text layer of a PDF') with a scope qualifier that separates it from OCR-based readers. It effectively distinguishes itself from sibling read_image_text via 'Does not OCR scans', though it never names a sibling outright.

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?

Gives clear when-not guidance ('Does not OCR scans') and input routing ('Send base64 or a public URL'), plus the constraint that private addresses are refused. No alternative tool is named for scanned documents, which keeps it short of a 5.

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