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

Annotations only provide destructiveHint=true, and the description substantially expands on that: soft-delete semantics, 5-day retention then auto-purge, submission records preserved until permanent purge, and the restore path. This is exactly the behavioral context an agent needs beyond a bare destructive flag, and it does not contradict the annotations (destructiveHint=true aligns with moving to trash).

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 sentences with no filler: core action and scope, recovery window with the restore path, then permissions and submission handling. The most decision-relevant fact (this is a soft delete, not a permanent deletion) is front-loaded in the first sentence.

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 single-parameter mutation tool with a present output schema and a destructiveHint annotation, the description covers action, scope, retention, recovery, permissions, and side effects on submissions. Remaining gaps such as idempotent re-deletion or permission-denied error codes are minor edge cases, and the output schema covers return-value expectations.

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 100%, so formId is already documented as 'The form UUID to move to trash.' The description adds the 'current team' scoping, which usefully constrains which formId is valid, but it provides no additional format or validation guidance beyond the schema. Baseline 3 is appropriate when the schema already carries the parameter documentation.

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 opens with a specific verb and resource: 'Move a form into the trash (soft delete) in the current team,' which immediately clarifies not only what the tool does but its non-permanent nature. It also differentiates from siblings by naming restore_form as the inverse and by making the resource (form) distinct from delete_form_translation and delete_question. An agent can disambiguate without opening schemas.

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?

It names restore_form as the explicit recovery alternative, tells the agent the hidden-from-list_forms consequence, and states the permission precondition (form owner or team owner/admin). It stops short of an explicit when-not-to-use directive, but since no hard-delete sibling exists, the guidance is clear and actionable for the tool family.

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