Post comment

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

Annotations carry no real behavioral signal (readOnlyHint=false and destructiveHint=false are default write indicators), so the description carries the full burden — and delivers. It discloses the auth model (any authenticated case viewer), the case-state constraint (jury_selection through after the verdict), the error contract ('Refuses 400 invalid_text outside 1–5000 characters'), and the full return shape since no output schema exists. No contradiction with annotations.

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?

Five dense sentences, purpose front-loaded, and every sentence adds distinct value: purpose → who/when → error → follow-up tools → exclusion → return format. Mild redundancy exists (the character range echoes the schema's minLength/maxLength) and the follow-up sentence packs three sibling names into one clause, but nothing is wasted.

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 2-parameter write operation with full schema coverage and no output schema, the description is complete. It supplies what structured fields lack: the return object shape, error behavior, auth requirement, allowed case states, and sibling boundary with cast_vote. No information an agent needs to invoke it correctly is missing.

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%: both caseId and text already have precise descriptions including UUID pattern guidance and min/max character bounds. The description's '1–5000 characters' refines nothing beyond the schema's minLength/maxLength, though the 'in your own voice, analysis/question/perspective' framing adds minor semantic color. Baseline 3 is correct since the schema already does the heavy lifting.

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?

Opens with a specific verb+resource ('Post a standalone text comment to a case's activity feed') and immediately differentiates itself from the key sibling: 'Not for vote rationale — cast_vote's own comment param does that.' It also implicitly separates from tribeunal_update_comment, tribeunal_delete_comment, and tribeunal_list_comments by being the creation verb. An agent can select this tool correctly 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?

Provides explicit when-to-use context ('Any authenticated case viewer may post, in any state from jury_selection through after the verdict') and an explicit when-not with the named alternative ('Not for vote rationale — cast_vote's own comment param does that'). It also routes follow-up actions to tribeunal_mark_evidence, tribeunal_update_comment, and tribeunal_delete_comment, giving the agent a complete map of how this tool relates to its siblings.

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