Price a bid

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description adds plan gating that annotations cannot express — benchmark and position require the Pro plan — which is genuinely decision-relevant. Return shapes are not described, but an output schema exists, so that burden is lifted.

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 one-line purpose, then organized as one bullet per `kind` so an agent can jump straight to its mode. Dense but every line carries parameter or mode information. The heavy abbreviation and tight line-wrapping cost some readability without adding real waste.

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 two-parameter dispatcher over five sub-operations with an opaque filters object, the description covers mode selection, required filters per mode, enum vocabularies, plan gating, and one cross-tool prerequisite. With an output schema present, return values need not be explained. An agent has enough to call this correctly.

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 `filters` is an open additionalProperties object, so the schema supplies essentially nothing; the description carries the full burden and does so well, naming filter keys and decoding enums (FFP | T&M | CPFF | CPAF | LH, 8A | SBA | SDVOSBC | WOSB | HZC | NONE, HS | AA | BA | MA | PHD, SCA | DBA, contains | exact, current | potential | obligated). It falls short of 5 because types, defaults, and whether filters are mutually compatible across modes are left implicit.

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 the resource (pricing/rate evidence for a bid) and then enumerates five distinct sub-operations with the specific artifact each returns (contract value distribution, rank of a value, GSA CALC ceiling rates, SCA/DBA rates, rate spread). An agent can tell what each `kind` value yields. It does not, however, distinguish this from the `market` sibling, so differentiation is incomplete.

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?

Per-mode requirements are spelled out (e.g. benchmark/position need `naics`, position needs `value` as a string, labor_rates needs `labor_category`), and it routes cross-tool for one case: "For one place, get the WD first and read its rates." That is real when-to-use guidance. What is missing is any explicit rule for choosing between `benchmark` vs `position` vs `market` when several could apply.

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