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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely new behavior — the heuristic thresholds (>=80% non-milestone tasks with plannedCost, active rate card exists) and the cost/fidelity profile. It doesn't mention permissions or failure behavior, keeping it short of a 5.

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: purpose first, then exact return semantics, then usage routing. Every sentence carries information an agent needs to call and interpret the tool.

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, yet the description fully specifies the three possible return values and the conditions producing each, plus when to call it. Nothing needed for correct invocation or interpretation is missing.

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% and the single projectId parameter is never named or described, though 'for a project' weakly implies it. With one required param and no format/ID-type guidance, the description only marginally compensates.

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 (probe) and resource (cost-attribution path EVM will use for a project), and enumerates its return values with thresholds. It is clearly distinguishable from calculate_evm and other EVM siblings because it is a diagnostic rather than a computation.

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?

Explicitly frames itself as a 'cheap pre-flight before calling calculate_evm' and gives the reason (warn the user when fidelity is low), naming the alternative tool and the condition that selects it.

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