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

Beyond the annotations (which already cover read-only, idempotent, closed-world), it discloses the auth model (no API key for public ids; org API key or OAuth token with forms:read for form:<id>), the complete not-found surface (draft, archived, deleted, unknown id, other organization), and a privacy guarantee that applicant data is excluded. This is exactly the kind of context annotations cannot express.

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?

Purpose and the id-provenance rule are front-loaded, and most sentences carry distinct information. The trailing 'Workers AI stays off' is opaque jargon that does not clearly earn its place, and the auth clause interrupts the otherwise consistent content description.

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 single-parameter read tool with an output schema, the remaining burdens are auth, failure modes, and payload contents, and all three are addressed. Return fields are enumerated anyway (id, title, text, url, metadata, trialUrl), so an agent has nothing left to guess about before calling.

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 100%, so the prefix conventions are already documented and the baseline is 3. The description still adds real meaning by tying the id to a prior search result and by attaching a distinct authorization consequence to the form: prefix, which the schema does not state.

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 first sentence names a specific verb and resource ('Read one document') and scopes it to the id returned by search. It also distinguishes the payload from the sibling get_form ('metadata includes the same share links as get_form'), so an agent can tell the two apart without opening either schema.

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 establishes the entry condition (the id must come from a prior search hit) and enumerates which id namespaces are eligible (doc:, template:, form:). It stops short of explicitly saying when to prefer get_form over fetch despite noting the metadata overlap, so routing between the two is still partly inferential.

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