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

Goes well beyond the destructiveHint annotation by defining blast radius: the message is never sent, the rest of the plan is unchanged, and cancelling records the actor plus a case activity entry. It also explains the state machine restricting which texts are eligible, so an agent understands consequences rather than just 'this is destructive'.

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 tight sentences: purpose first, then side effects, then exclusion states, then scope reassurance. Every sentence carries information and none repeats the title verbatim without adding meaning.

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 destructive mutation with no output schema, the description supplies the state preconditions, side effects, and non-effects an agent needs before calling. The remaining gap is parameter-level guidance, which annotations and schema only partially cover.

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 only 33% (6 params, only source and idempotency_key documented), and the description mentions no parameter names at all. It never clarifies that 'text' is a queued-text UUID tied to 'case', or what 'source'/'environment' select, so it does not compensate for the coverage gap.

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), a specific resource (one approved plan's text) and the exact state it applies in (waiting for the customer's texting hours). That state qualifier cleanly separates it from summer_cases_queued_texts_list, which only reads the queue.

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?

Explicitly states the valid precondition (queued, awaiting texting hours) and the exclusion cases ('sending, sent or has an unknown result cannot be cancelled'), which is strong when/when-not guidance. It does not name an alternative tool for texts that cannot be cancelled, so it falls short of a 5.

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