workflowmoves_outreach_finish

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

Beyond the annotations (write, destructive, non-idempotent) it discloses that the call returns a retained background job rather than completing synchronously, that uncertain sends stay in a claimed state, and that conditional inference/download effects are governed by danceflow_component. That is meaningful context the annotations cannot express. It is not a 5 because what 'retain evidence' actually persists and what happens on a rejected token are left unexplained.

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 tight sentences with no filler, and the primary effect (retain evidence, release mutex) is front-loaded before the follow-up and effect-flag notes. The density of internal jargon ('mutex', 'claimed', 'base effect flags') costs some readability but not economy.

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?

An output schema exists, so return values needn't be explained, and the description covers the async job model and effect flags. What is missing is material for a destructive, non-idempotent tool with an opaque eight-field payload: no statement of required prior state, no consequences of a failed ownership check, and no guidance on where root/key/token come from.

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 50%: the permissions object documents its flags, but the four required argument fields (root, key, token, receipt) carry only regex constraints, no semantics. The description gestures at their roles — the owned mutex maps loosely to token/key/root and 'verified send evidence' to receipt — but never states it explicitly, so the mapping stays inferential.

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 names a concrete operation: retaining verified send evidence and releasing the exact owned mutex, with uncertain sends left claimed. That is specific enough for an agent to know this finalizes an outreach send rather than lists or claims one. It stops short of a 5 because it never names the sibling steps (workflowmoves_outreach_claim / inspect) that bracket it, so the position in the workflow must be inferred.

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?

There is implicit sequencing guidance ('release only the exact owned mutex', 'uncertain sends remain claimed') and an explicit follow-up ('poll danceflow_job_status'). However, no alternative is named and no prerequisite is stated — an agent is not told it must have claimed a mutex first, nor when to choose this over the outreach_claim or outreach_inspect siblings.

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