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

Annotations only declare readOnlyHint=false; the description adds real behavioral context beyond that: no vote/approval required and the main document is left intact ('does not replace main'). It also flags the document as optional. Auth detail is left to the contributor_key schema description rather than the prose.

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 short sentences, purpose front-loaded, no padding. The clipped final phrase 'does not replace main' is slightly terse but still earns its place by conveying non-destructiveness.

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 write tool with a deeply nested document object, six params, low schema coverage and no output schema, the description covers the behavioral story but not the input contract. An agent knows what a fork does but not how to build the required payload.

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 17%, so the description must carry the burden, yet it only addresses one of six params: 'Optional document carries your own changed text.' The required fields (request_id, from_revision_id, title, reason, contributor_key) and the nested clause/preamble structure get no prose explanation.

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: 'Create an independently editable alternative from a saved revision,' which clearly reads as a fork operation. It distinguishes itself from siblings implicitly via 'does not replace main,' but never names the alternative tools (edit_agreement, adopt_agreement, revert_agreement) it sits beside.

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?

'No vote or approval required' and 'does not replace main' hint at exclusion conditions versus approval-based siblings, but usage guidance is only implied. There is no explicit when-to-use statement or named alternative for an agent to route against.

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