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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), and the description adds genuinely new facts: it operates on a supplied wait-for graph and returns an object with 30 fields including `action` and `acyclic`, plus a $0.1 USDC cost. The pricing and result-shape disclosures are the kind of context annotations cannot carry.

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 first sentence is well front-loaded, but the remainder is a garbled run-on that jams usage routing, a return-shape summary, and a price into one semicolon-joined clause. It is short but not cleanly structured.

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?

Safety and return values are covered by annotations and the output schema, and both parameters have schema text. What is left unexplained is the shape of the wait-for edges themselves, the single thing an agent most needs to construct a valid call.

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 both parameters are already documented at baseline. The phrase "supplied wait-for graph" hints that `wait_for_edges` carries the graph structure, but it does not clarify the edge object format, which matters because `items` is an untyped `{}`.

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: "Detect a deadlock in a supplied wait-for graph." It explicitly contrasts itself with the nearest sibling, `assess_operation_behaviour_drift`, so an agent can distinguish the two 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 an explicit routing rule: use this rather than `assess_operation_behaviour_drift` for agent deadlock, not operation behaviour drift. That is a clear use-case plus named alternative, though it only names one sibling and offers no other preconditions or exclusions.

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