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

Annotations only declare the safety profile (non-read-only, non-destructive, idempotent, closed-world); the description goes well beyond by explaining the output package (single ZIP, JPEG passthrough, PNG with soft-mask transparency, manifest.csv with page/size/colour space/compression) and the self-check where the ZIP is re-opened and every file verified against its reported size before a link is issued. It also discloses failure handling for unsupported formats and the hard limit on password-protected PDFs. This is exactly the extra context annotations cannot carry.

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 trigger condition is front-loaded in the first sentence, then inputs, then output shape, then verification and exclusions in a logical flow. It is a dense paragraph rather than a long ramble, though the ZIP-verification detail could be compressed without losing agent-relevant meaning.

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?

Despite six parameters, a nested file object and an output schema, the description covers what an agent needs: trigger, input intent, return packaging, verification behaviour and hard exclusions. Nothing required to decide whether to call it correctly is missing.

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 every parameter including pages syntax, dedupe defaults, and the images selector. The description restates pages, minimum width/height ("to skip icons") and dedupe default true but adds no format or edge-case detail the schema does not already supply. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb set (extract, save, download) and a precise resource (images/photos embedded in a PDF), so there is no ambiguity about what the tool produces. It does not name its sibling list_pdf_images or explain the relationship between them, so an agent must infer the boundary from the schema instead of the prose.

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?

"Use this when the user wants to extract, save or download the images or photos embedded in a PDF" gives a clear trigger condition tied to user intent. The closing sentence adds useful exclusions (password-protected PDFs, page rendering, vector drawings, OCR), but the alternative tool list_pdf_images is never positioned as the discovery step this tool depends on.

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