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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the description's job is to add specifics, and it does: save_as_sop=true causes a write to the handbook (matching article or a new one), and a repeated idempotency_key prevents double-writing. That side-effect detail goes meaningfully beyond the boolean hints. It does not disclose permission requirements, whether a new article is created silently, or any reversibility of the handbook write.

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?

The content is dense but front-loaded: what it does, the screen it mirrors, then the save_as_sop branch and the idempotency rule. The parenthetical enumeration of status values duplicates the schema enum and could be dropped. No filler sentences otherwise.

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 7 parameters, 14% schema coverage, no output schema, and a mutation that can write into the handbook, the description covers the headline behavior but leaves real gaps: sop_id's role when save_as_sop is false, whether answer is required alongside a status, and what the tool returns. Adequate to attempt a call, not complete enough to be confident about edge cases.

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 only 14%, so the description must carry most of the semantic load. It clarifies question_id's provenance, the save_as_sop side-effect, and status values — but status is already an enum in the schema, so that is partly redundant. The low-coverage fields sop_id and notes get only the vague glosses 'sop_id it belongs to' and 'notes', and it never says whether answer is optional (allowing a pure status change), which matters for a 7-parameter write tool.

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 states a concrete verb set and resource: it answers or files a logged question and mirrors the Handbook > Admin > Questions screen, enumerating the fields it writes (answer, status, sop_id, notes). An agent can tell this is a question-resolution/status-update tool rather than an article editor. It stops short of explicitly distinguishing itself from the sibling log_handbook_question, which creates the very questions this tool consumes.

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?

Usage context is clear: it operates on an existing logged question whose question_id comes from read entity sop_questions, and it gives explicit retry guidance ('pass the same idempotency_key when retrying'). It also explains the conditional branch for save_as_sop. What is missing is an explicit inverse — e.g. 'to create a new question, use log_handbook_question' — and any statement about when not to use it.

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