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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds genuine beyond-schema context: the documents are public, they 'disclose, do not gate', and the payload is raw markdown rather than a structured object.

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?

Front-loaded with the core action and well sized for a one-parameter tool. Minor waste: the trailing 'Example: call legal_get with arguments {"document":"<document>"}' is filler with a non-substantive placeholder, and 'CO 311' is an opaque internal reference.

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?

Covers what the tool returns (raw markdown), the access model (public, read-only, non-gating), and the full set of documents in prose. With no output schema, the explicit return note and the enumerated instrument list make this complete enough to invoke correctly.

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% and the enum already documents all six values, so the schema carries the load. The description partially duplicates this but its inline list ('terms | privacy | dpa | retention') omits submission and acceptable-use, which is an incomplete restatement rather than added meaning.

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 ('Fetch a ComOS legal instrument as raw markdown') and enumerates the concrete document types it returns, which is far more than a restatement of the name. It also points at the sibling relationship indirectly via 'read them the way you read the pricesheet' (federation_pricesheet), though it never names a tool alternative 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 real usage context — 'these are the terms an agent (and its manager) operate under' and 'discloses, does not gate' — which implies when to reach for it. But there is no explicit when-to-use vs. when-not or a named alternative, so guidance remains implied rather than stated.

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