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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds genuine value by clarifying the destruction is scoped to the local draft ('No Meta write') and that a stale digest is rejected, but it does not say whether the denial is reversible or what happens on digest mismatch beyond rejection.

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?

Four short clauses, front-loaded with the action and its inputs, with no filler. Every clause contributes distinct information (inputs, effect, digest behavior, blast radius, scope).

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?

An output schema exists so return values need not be described, and annotations carry the safety profile; the description completes the picture with input provenance and the no-Meta-write boundary. The undocumented connection_context parameter is the only material gap.

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 carry the load. It names approval_ref and expected_plan_digest and points to operations_get_approval as their source, but leaves connection_context entirely unexplained and adds no format or validity detail beyond what the schema patterns already enforce.

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 (Deny) against a specific resource (a prepared operation / draft) and immediately differentiates itself from the operations_confirm_* siblings by clarifying it invalidates without applying. An agent can select this over any confirm tool without opening the schema.

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?

Tells the agent where the inputs come from (operations_get_approval) and what the effect is (invalidate the draft rather than apply it), which implicitly defines when to reach for it. It stops short of explicitly naming the confirm tools as the alternative path or stating exclusions such as approval types it does not support.

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