mutate_declaration_draft

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

The description discloses two key behaviors: it is a mutation (write) operation and returns an exact rollback receipt (suggesting revert capability). However, with no annotations provided, the description carries the full burden, and it doesn't mention expected_version's optimistic-concurrency role, required evidence, or any rules about field-specific value types.

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?

A single clean, front-loaded sentence with zero waste. It states action, scope, and return value compactly.

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?

The output schema presumably documents the rollback receipt, so the description needn't detail that. However, for a mutation tool with no annotations, key contextual details are missing: the expected_version concurrency mechanism, the need for evidence_ids (up to 16), the field-value-type coupling, and what the rollback receipt enables (revert usage). It's adequate but leaves consequential gaps.

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%, so the description must compensate. The description clarifies the single top-level `request` parameter (a MutateDraftInput) and reinforces that exactly 'one typed draft mutation' is applied, which adds meaning to the nested structure. However, it doesn't explain that only the relevant value field (text_value, boolean_value, decimal_value) should be set per the DraftField enum, which the schema itself doesn't clarify.

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 ('Apply one typed draft mutation') and clearly indicates the tool produces a rollback receipt. It distinguishes from siblings by focusing on mutation application, though it doesn't explicitly contrast with revert_declaration_mutation which is its natural counterpart.

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?

The description implies this is the write operation for editing a draft, but offers no explicit guidance on when to use mutate_declaration_draft versus revert_declaration_mutation or validate_declaration_draft. No exclusions are stated, but the tool family makes the purpose reasonably inferable.

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