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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds a genuine behavioral guarantee beyond that: the tool returns only sources the calculator actually cites, which tells the agent the result is a faithful subset rather than an enriched bibliography. It says nothing about size, pagination, or failures, 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 short sentences, front-loaded with a concrete question that frames the purpose before the payload list. The rhetorical opener is a small stylistic cost rather than filler, and the closing fidelity clause earns its place as a scope constraint.

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?

An output schema exists, so the shape of the returned sources and citations need not be restated, and annotations carry the safety profile. The description covers what is returned and its fidelity constraint; only the prerequisite that the slug must reference an existing calculator is left implicit, a minor gap.

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%: both slug and the full/summary detail enum are documented in the schema itself with defaults and meaning. The description adds no parameter-level information (the citation-format list describes output, not input), so the baseline 3 applies.

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 ('Returns a calculator's sources as it cites them') plus the exact payload: codes/standards, standards pages, and citation formats (plain, APA, Harvard, BibTeX). This clearly separates it from get_calculator, get_example, and the create_* siblings, which deal with the calculation or its output rather than its provenance.

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?

The leading question ('Where does a figure come from, and how is it cited?') implies the provenance/citation use case, and 'It adds no source the calculator does not cite' sets an expectation of scope. However, it never states when to prefer this over get_calculator or how to reach it, so the usage trigger is inferred rather than explicit.

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