revert_declaration_mutation

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Exactly once' hints at idempotency semantics (potentially destructive/reversible-of-reversible), but the description doesn't state what the outcome is, whether the operation is reversible, concurrency implications (expected_current_version parameter implies optimistic locking), or what failure states look like. The 'exactly once' point is useful but leaves major behavioral gaps for a reverting/mutation tool.

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?

The description is a single, compact sentence that establishes the core purpose in an efficient manner. It's appropriately short given the tool complexity is largely captured in the schema, though the ambiguous 'exactly once from its receipt' phrasing could arguably be clearer with one more modifier.

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?

This is a complex mutation/revert tool with an output schema, nested input with concurrency semantics (expected_current_version), and no annotations. The description is too sparse given this complexity: it doesn't explain the revert process state machine, what happens to versions, or how the 'exactly once' guarantee is enforced. The output schema exists but the tool's behavioral semantics around versioning and receipts are under-documented.

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 there is a single nested parameter 'request' with substantial structure. The description mentions 'receipt' but doesn't explain the expected_current_version parameter's role in optimistic concurrency, nor what the receipt input should contain. The schema defines the fields but the description adds no additional semantic guidance about how to construct the request or what the relationship between receipt and version is.

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 'Revert one confirmed draft mutation exactly once from its receipt' uses a clear verb (revert), specific resource (confirmed draft mutation), and a distinctive qualifier ('exactly once from its receipt') that differentiates it from the sibling mutate_declaration_draft. It's clear this is an undo operation, but the phrase 'exactly once from its receipt' is slightly opaque without context on what 'receipt' refers to.

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?

There is no guidance on when to use this vs. alternatives. The description implies usage (revert a draft mutation) but doesn't state prerequisites, such as the need to have a confirmed mutation receipt from a prior mutation, or any exclusions/constraints relative to sibling tools like mutate_declaration_draft or prepare_declaration_review.

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