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

Annotations already declare idempotentHint=true, destructiveHint=true, readOnlyHint=false, openWorldHint=true. The description adds genuine context beyond these: changes are audited, assignment never grants approval rights, completion cannot clear proof/export gates, comments remain append-only, and notifications are queued but delivery is not confirmed. The idempotency claim aligns with the annotation; no contradiction found.

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?

Six dense sentences, front-loaded with the purpose and revision requirement followed by behavioral caveats. Every sentence carries a meaningful constraint (audit, authorization, approval, proof gates, append-only comments, notification semantics), so there is no fluff. Dense, but the complexity of the tool justifies the length.

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?

No output schema exists and the description omits return-value behavior entirely. The tool's core complexity — the update oneOf (deadline/assignment/clarification) and the six-way target oneOf — is never described, so an agent has no guidance for constructing the hardest part of the call. Behavioral caveats are thorough, but structural guidance is missing for a tool this complex.

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 40%, so the description must compensate. It adds meaning for expectedRevision (must come from helvabase_work_items) and idempotencyKey (audited/idempotent behavior). However, the most complex parameter, update, is only loosely connected — the verbs 'complete, cancel, reopen' map to status changes but don't align obviously with the schema's kind values (deadline, assignment, clarification), which could mislead an agent constructing the update object.

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 set (update, assign, reassign, complete, cancel, reopen) acting on an existing dossier action, and names the prerequisite tool helvabase_work_items that supplies the exact revision. This clearly distinguishes it from siblings like record_work_item (creation) and work_items (listing) — an agent can tell the purpose apart without inspecting 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?

Explicitly names helvabase_work_items as the source of the required revision, giving the agent a clear prerequisite step. It also sets a scope constraint ('targets must exist in the current authorized dossier'). However, it gives no explicit when-not-to-use guidance or alternative routing beyond the implied update-vs-create distinction against record_work_item.

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