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

With no annotations supplied, the description carries the full burden and largely meets it: it discloses the shape of the response (calc-core function, statute, source URL, formula-catalog ids) and the read-only, reference nature of the call. It does not say whether the catalog is exhaustive — the trailing 'etc.' implies it is not — nor anything about result size or ordering, which matters for a bulk reference 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?

Two sentences plus a colon-led inventory, front-loaded with the resource before the workflow instruction. The parenthetical calculator list earns its place by making the scope tangible, though the sentence structure is slightly dense and the 'etc.' weakens precision.

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 parameterless reference tool with no output schema, the description does the necessary work by explaining what the payload contains and how to follow up with get_formula. Completeness is only slightly short of ideal because the extent of the catalog and the downstream handoff to get_calculator_template/fork_calculator are not addressed.

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 there is no parameter semantics to add beyond what the empty schema already conveys. Baseline 4 applies; the description correctly implies a global, unfiltered listing rather than implying any hidden input.

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 identifies the resource concretely — existing Comp Desk calculators (SLU, LWEC, CCP, AWW, Burns) — and enumerates exactly what is returned: calc-core function, statute, canonical source URL, and formula-catalog ids. It is distinguishable from the calculate_* siblings because it is a reference/lookup rather than a computation. It stops short of a clean leading verb (e.g., 'List'), so the agent must infer that this is a no-argument retrieval tool.

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?

'Start here, then call get_formula for the algebra' gives explicit sequencing relative to a named sibling, and 'use this to build on or improve an existing calculation instead of starting from scratch' states the motivating condition. What is missing is any when-not guidance — e.g., that an agent wanting to compute a fresh award should go straight to calculate_* rather than reading the catalog.

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