Phone Claim

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

With no annotations, the description carries the full behavioral burden and does so: it explains first-caller ownership, race resolution by the server, both return outcomes ('yours' vs 'taken'), downstream display in phone_listen/phone_watch and the person's page, and the 3-minute default. It omits only edge cases like invalid `n` or how to release a claim.

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 description front-loads the claim action and then layers concurrency, return values, side effects, selection rules, and the default timeout. It is dense but every sentence contributes; minor tightening could remove overlap between the opening and the later 'Claim the untagged notes' instruction.

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?

Given zero annotation coverage, zero schema coverage, and an output schema that can handle return structure, the description still explains the coordination semantics, return meanings, and side effects an agent needs. It is nearly complete for correct invocation, though it leaves out edge cases such as invalid note ids or how to relinquish a claim.

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 0%, so the description must define all three parameters; it explains `n` as the person's note, `by` as the caller's identity, and `why` as a short free-text reason with an example. It could be stronger by stating the expected source/format of `by` (your `who`), but it adds meaningful semantics beyond the bare schema.

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 the specific action of claiming a person's note `n` before acting on it, and distinguishes claimed untagged notes from notes already tagged with `for`, including a default owner after 3 minutes. An agent can tell this is the note-ownership tool rather than phone_listen, phone_watch, or phone_status.

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?

It gives explicit timing ('BEFORE you do it') and selection rules: claim only untagged notes you will act on; notes with `for` already belong to another agent; unclaimed notes default to the team lead after 3 minutes. This covers when to call and when not to.

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