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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds substantially more: idempotency semantics ('recording the same insight twice replaces your earlier note; a pinned note is left as it is'), the required 'act' scope, that the call is free, and the return payload ('the top of their board with move ids'). This is behavior the agent could not infer from structured fields.

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-loaded with the core action and organized into WHEN, constraints, cost/scope, and WHAT COMES BACK sections. It is on the verbose side, but nearly every sentence carries distinct information, so little 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?

No output schema exists, but the description explains the return value in prose ('the top of their board with move ids'). Combined with scope, cost, idempotency, and content constraints, an agent has everything needed to call this correctly.

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 100%, so all three parameters are already documented in the schema, including the kind enum and the source_move_id uuid origin (list_feed). The description reinforces the 10-500 character and one-sentence constraints but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema 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?

States a specific verb and resource: 'Write one durable thing you have learned... into AfterLaunch's Memory,' and defines Memory as the record drafts are written from. It distinguishes itself from siblings by explicitly excluding restatements of get_snapshot/get_kb_page and by passing voice rules to record_voice_rule. An agent can tell this apart from record_claim or record_content without opening 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?

Explicit WHEN clause ('the moment the founder tells you something that will still be true next month and that AfterLaunch could not have measured itself'), plus concrete negative guidance ('Never record chatter, a passing mood, a restatement of get_snapshot or get_kb_page, or anything you inferred'). The kind schema description additionally routes voice rules to record_voice_rule.

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