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

Annotations only flag destructiveHint/idempotentHint; the description goes further by disclosing the actual consequence (reverts to draft rather than deleting), a precondition gate ('when its current state permits'), and the exact retry contract with idempotencyKey. That is meaningful behavior an agent could not infer from the structured fields alone.

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 ordered as consequence, verification, then failure handling — front-loaded with no filler. Each sentence carries distinct operational information.

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 3-param mutation with no output schema, it covers outcome, sequencing, and retry adequately. The main remaining gap is that 'when its current state permits' never says which states permit it, leaving the agent to guess whether the call will fail.

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 100% and every parameter is documented in-schema, including the idempotencyKey retry rule. The description's sentence about retrying the identical body and key largely restates the schema text rather than adding new meaning, so baseline 3 applies.

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 ('Cancel ... schedule') plus the concrete outcome ('return it to draft'), which distinguishes it from company_delete_post and company_reschedule_post by implication. It never names a sibling explicitly, so the differentiation must be inferred rather than read.

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?

Gives a post-call verification step ('verify with company_get_post') and an explicit retry protocol for lost responses, which is real operational context. It stops short of naming alternatives (reschedule vs. delete vs. cancel-approval) or stating when not to use it.

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