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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, and the description still adds real value: the untrusted-data/prompt-injection warning and the privacy note about sources are behavioral context the annotations cannot express. It does not describe pagination or return format, but nothing contradicts the safety hints.

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?

Three tight sentences with no filler, front-loading what is read before the safety admonitions. Every clause earns its place.

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 usefully enumerates the returned content (proposal, revision, source evidence, conflicts) and adds the injection/privacy context appropriate for reading untrusted documentation. The only real gap is parameter guidance, which is left entirely to the schema.

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 0% and the description mentions neither change_id nor account_id, so it does not compensate for the documentation gap. The parameter names are largely self-explanatory UUIDs, but there is zero added meaning such as scoping, format, or where a change_id is obtained.

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 uses a specific verb+resource ("Read a documentation proposal") and enumerates the payload (exact revision, source evidence, unresolved conflicts), which maps cleanly onto the get_knowledge_change name. It does not, however, explicitly contrast itself with siblings like get_knowledge_page or get_knowledge_source, so an agent must infer the boundary.

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 only implied through the phrase "before editing or publishing," which situates the call in a workflow but names no alternative tool or condition that selects this one over get_knowledge_page/get_knowledge_source. The "never publish without the user's instruction" line is a guardrail, not a use-case selector.

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