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

Goes well beyond the annotations: destructiveHint=true already flags deletion, but the description adds that removal propagates to the Sparade urval list on firmafakta.se, and that an id not saved by the account is 'refused, without charge' — disclosing the error semantics of a repeat delete that the idempotentHint alone doesn't spell out.

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 short sentences, front-loaded with the action and its permanence, then the id source, then the failure case. Nothing is redundant or padded.

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?

With an output schema, complete annotations, and full param coverage, the description only needs to supply what structured fields can't: the external mirror effect and the invalid-id behavior. Both are present for this one-parameter destructive tool.

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?

Single parameter with 100% schema coverage whose description already says 'the saved segment's id, from firmafakta_load'. The description only restates that provenance, so it adds no syntax or format meaning beyond the schema; 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 and resource ('delete a saved segment') plus the crucial permanence scope ('for good, also from Sparade urval on firmafakta.se'). It implicitly distinguishes itself from the sibling mutation tools firmafakta_save/firmafakta_update by being purely destructive, so an agent can select it 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 prerequisite data provenance ('give its id from firmafakta_load'), which is actionable guidance for correct invocation. It lacks an explicit when-not/alternative clause, but the destructive nature makes the use case unambiguous.

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