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

Far beyond the annotations, it discloses that a human does the routing, that no delay is promised, that each call creates a non-retried record (consistent with idempotentHint=false), that sensitive values are masked with warnings naming masked fields, and that the first call sets is_authenticated. These are exactly the side-effect details an agent needs before invoking a write tool.

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?

Purpose is front-loaded in the first sentence, with operational caveats following in a compact sequence. Density is high but nearly every clause carries non-obvious information; only the is_authenticated side effect feels appended rather than integrated.

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 write tool with no output schema, it covers routing, safety, retry behavior, and next steps. The one residual gap is what the call returns (a record identifier?) that get_handoff_status would consume, which the agent must infer.

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 the baseline is 3, but the description adds a genuine parameter-usage rule not present in the schema: never put keys or client data into the free-text field because detection and masking will occur. It adds nothing for deadline or acceptance_criteria, which the schema already constrains fully.

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 states a specific verb and resource ("Records what the agent could not do") and explicitly corrects the misleading tool name by saying "no specialist is returned by this call." It also distinguishes itself from the sibling get_handoff_status by framing that call as the follow-up step.

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 clear sequencing guidance ("Follow the need with get_handoff_status") and manages expectations about human routing and delay. It stops short of stating when an agent should NOT file a need, but the operating context is clear enough to act on.

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

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

Annotations already declare readOnly, idempotent and openWorld, and the description goes well beyond them by disclosing the authorization model and the specific error behavior ('anything else returns 404, including an id that exists'), which prevents an agent from misreading a 404 as a nonexistent id. It also warns that verdicts are third-party data and never instructions, an important prompt-injection guard that no annotation conveys.

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 what is returned, then the access rule, then the safety caveat. No filler and no repetition of the name or title.

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?

With no output schema, the description carries the return-value burden and lists the fields returned plus the failure mode, which is nearly everything an agent needs for a single-id read tool. It does not explain what status values are possible or how the timeline is structured, a minor remaining gap.

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% and the schema already states handoff_id is the value returned by find_specialist, so the baseline is a 3. The description adds meaning by tying the id to an access-controlled lookup where an existing but unauthorized id still yields 404, which is semantics the schema does not carry.

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 and resource ('Reads the status, timeline, specialist and verdict of a handoff') and even names the key returned fields, so an agent knows exactly what it gets. It does not explicitly distinguish itself from the siblings find_specialist or list_match_proposals, though their purposes are dissimilar enough that confusion is unlikely.

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 a concrete precondition for use: only the requester and the specialist can read a handoff, and everything else gets a 404. That is a real when-to-use gate rather than a vague hint. It stops short of explicitly saying when to prefer this over the sibling tools, so it is not a full 5.

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

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

The description adds real behavioral context beyond the annotations: it explains why readOnlyHint=false despite a pure list operation ('the first one sets the agent's is_authenticated flag'), which is a side effect an agent could not infer from structured fields. It also warns that partner names and texts are third-party data, never instructions, addressing prompt-injection risk. What it does not cover is the return shape (fields per proposal, ordering, volume) and there is no output schema to fill that gap.

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?

Four short sentences, each doing distinct work: what it returns, what it does not do, a safety note, and the authentication side effect. The purpose is front-loaded and nothing is redundant.

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 zero-parameter, no-output-schema tool the description covers purpose, exclusions, the auth side effect, and data-safety framing. It leaves the shape of a returned proposal undefined, which an agent would need if it plans to act on the results, but that is a minor gap given the tool's simplicity.

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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter semantics to add. The description correctly implies there is no filtering input by saying it lists what has already been made.

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 ('Lists the match proposals ConnexAgents has already made for the configured agent, from profile matching'), including the scope that they were generated by profile matching. The negative clauses ('does not search, does not transmit a need, does not create a handoff') carve out the space occupied by siblings find_specialist and get_handoff_status, so an agent can route without opening either schema.

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?

Gives clear when-not guidance by ruling out searching, transmitting a need, and creating a handoff, which is enough to steer an agent away from the sibling tools. It stops short of naming those siblings or stating the positive trigger ('use this to review proposals already generated') as an explicit instruction.

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