create_handoff

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

No annotations exist, so the description carries the full burden. It does disclose a real behavioral trait — the record is sealed with a sha256 receipt enabling tamper detection — but says nothing about what is returned (the receipt string? an id?), whether the record is persisted or only returned, or whether repeated calls overwrite state.

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?

A single sentence that front-loads the verb and resource, then closes with the differentiating seal mechanism. No filler, though the parenthetical field list is dense and could have been split for scannability.

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 an eight-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage, the description does the minimum: it names most fields and explains the receipt's purpose. It omits the two undocumented parameters and gives no information about the returned receipt, which an agent needs to chain into validate_handoff.

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 compensate; it does partially by naming six of the eight parameters (task, done, evidence, failed, unknowns, next_step). However, 'previous' and 'include_provenance' are never mentioned, and the nested evidence object's claim/how_verified semantics are left entirely to the schema's field names.

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 ('Build ... and seal') applied to a concrete resource (a task handoff record) and enumerates the record's fields inline. The sha256 receipt detail distinguishes it from validate_handoff and merge_handoff, though it never names those siblings 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?

The clause 'so the next agent can confirm it was not altered' implies the use case (end-of-task handoff to a successor agent), but there is no explicit when-to-use statement and no routing against validate_handoff or merge_handoff. Usage must be inferred from the field list.

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