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

Beyond the readOnly/idempotent/openWorld annotations, it discloses the ranking signals (word overlap, endpoint liveness, signed delivery record, 30-day uptime, speed), that the scoring rules are public at /hub/rules and applied uniformly including the operator's own entries (marked operator_affiliated), and that results carry a route_id plus an optional witnessed/audited hand-off. It also sets expectations honestly: "Hub signs nothing; this is advice, not a promise." That is material context the annotations cannot express.

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 action and the return in the first sentence, then ranking detail, then governance, then the hand-off offer. Dense but each clause carries information; the governance/rules sentence and the operator_affiliated note are the only slightly tangential material, though they do establish trust context.

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?

There is no output schema, and the description compensates by explaining what comes back: ranked entries with route_id and an optional hand-off offer for witness_record or transaction_audit. Together with the disclosed ranking criteria and the advice-not-guarantee caveat, an agent has everything needed to call this and interpret the result.

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 description coverage is 100%, so job, limit, include and category are already documented structurally. The description adds phrasing examples for `job` ("check a signed invoice", "weather alerts for Lagos") that convey the expected style of input, but it says nothing further about limit, include, or category. Baseline 3 with a marginal uplift from the examples.

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?

"Route a job... get back the best services and outside agents for it, ours or anyone else's, ranked by Agent Record evidence" gives a specific verb, resource, scope (own + third-party endpoints) and output shape. This clearly separates it from directory-style siblings like hub_directory and from the receipt-producing follow-ups witness_record and transaction_audit.

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 tells the agent how to invoke it ("State the job in plain words") with two concrete phrasing examples, and it names the downstream alternatives (witness_record, transaction_audit) as optional hand-offs from the answer. What's missing is any explicit when-not-to-use, e.g. when to browse hub_directory or use a specific check tool instead of routing.

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