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

Annotations declare it is a non-read-only, non-idempotent, non-destructive mutation, and the description goes beyond them by disclosing the audit trail kept (who opened it and when, who closed it before), the downstream effect (runs read it again as an open reason), the joined-reason exclusion, and the auth requirement (key cannot). That is genuinely additive behavioral context.

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?

Front-loads the action and stays to four sentences, each carrying distinct information (scope, effect, exclusion, auth). Phrasing is slightly awkward ('Open again a reason', 'It is open again') but nothing is 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?

For a one-parameter mutation with no output schema and covered annotations, the definition supplies the state change, the audit consequence, the exclusion rule, and the auth constraint. Only the response shape is unaddressed, which is acceptable given no output schema.

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 required reason_id with 100% schema description coverage; the schema already explains it comes from read_how_tommo_learns as a closed reason. The description adds no parameter-level detail beyond what the schema provides, so the 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 ('open again') and resource ('a reason of a tommo's synthesis'), and the 'closed by a person or Tommo' qualifier narrows scope. The inverse sibling close_a_learned_reason is implicitly distinguished, though not named explicitly.

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?

Gives a clear when-not condition: 'A reason joined into another is not opened: its decisions are counted in that one.' It also states the prerequisite that only a signed-in person can do this, not a key. No explicit pointer to a sibling alternative, but the applicability boundaries are concrete.

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