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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds one genuinely useful behavioral fact: 'Commits immediately', telling the agent there is no draft/confirm step unlike confirm_change or discard_change siblings. It says nothing about visibility defaults, assignee behavior, or what identifier comes back, so the added context is real but thin.

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 short sentences, front-loaded with the purpose, then the side effect, then the usage rule. Every clause carries information and nothing is repeated from the schema or annotations.

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 six-parameter creation tool with a nested object and no output schema, the definition covers what it creates, that it persists across sessions, that it takes effect immediately, and how to avoid duplicates. Remaining gaps — return value and how visibility defaults behave — are modest and partly mitigated by annotations.

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?

With schema coverage at 67%, the baseline is 3. The description reinforces the meaning of the kind values ('open question, pending decision, or follow-up') but adds no guidance on visibility modes, assignee_id semantics, or next_check_at formatting beyond what the schema text already states.

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 ('Record') and a concrete resource ('long-running unresolved item'), then enumerates the three cases ('open question, pending decision, or follow-up'), which map directly onto the kind enum. It is clearly distinguishable from resolve_open_item and list_open_items by virtue of being a creation action, though it never names a sibling 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?

'Use when a thread is left unresolved' gives an explicit trigger condition, and 'don't duplicate one already open' supplies a usable exclusion/precondition. No alternative tool is named, so the agent must infer that list_open_items is the check-first route, which keeps this short of a 5.

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