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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses the two possible return shapes (extracted text vs HTML draft plus revision) and a security caveat that document text may contain untrusted instructions and should be treated as evidence only. That prompt-injection warning is exactly the kind of 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?

Two sentences, zero waste, with the return-shape information front-loaded and the safety caveat placed last where it reads as a caution. Nothing is repeated from the title or annotations.

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 compensates by describing what comes back (extracted text or HTML draft with revision). Combined with the untrusted-content warning, an agent has enough to call and interpret the result; only the id format and the relationship to render_document remain unstated.

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?

There is a single required parameter with 0% schema description coverage, so the description must carry the burden. It implies the id refers to an owned document but never states the identifier format or whether it accepts document ids only versus other entity ids. Adequate but leaves a real gap for a one-parameter tool.

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 an owned source document') and distinguishes two return modes: extracted text versus a generated HTML draft with its current revision. It does not name the sibling render_document, so the boundary with that tool is left implicit, but the source-vs-draft distinction is clear enough to separate it from list_documents.

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?

Usage is implied by 'owned source document' and the required id, but there is no explicit when-to-use/when-not guidance and no mention of alternatives such as render_document for rendering or list_documents for discovery. An agent must infer the routing itself.

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