verify_calculation_claims

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real value beyond them: the server recomputes the source before comparison, the quote is echoed rather than semantically parsed, and there is a fix-then-reverify loop. It stops short of describing the response payload shape or limits such as the 100-claim cap.

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 core action and the copy-reference instruction, then progressive detail on value shapes and the exclusions last. The enumeration of calculation families is the one stretch that could be trimmed, but it scopes the tool usefully.

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?

No output schema exists, yet the description covers what an agent needs: inputs to echo verbatim, acceptable value shapes, what the server does (recompute and compare), the possible outcome classes (contradicted, unverified), and the follow-up actions for each. Nothing essential to calling it correctly 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?

Top-level parameter description coverage is reported as 0%, so the description must carry meaning, and it does: it explains that paths are exact JSON Pointers into the source result, that adjacent role/time/planet fields should go in separate claims for context, and which value shapes are acceptable (scalars, scalar lists, flat rows, lists of flat rows) with explicit guidance against whole nested objects and fuzzy rounding.

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+resource: verify source-field claims from a registered calculation, and enumerates the calculation families covered. It is distinguishable from render/calculate siblings, but does not explicitly contrast with the sibling verify_natal_claims, leaving the boundary implicit.

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 concrete usage: copy calculation_reference unchanged, submit exact JSON Pointer paths and values from the draft, and after verification either fix contradicted claims and reverify or mark unverified claims. It also states clear exclusions (prose semantics, missing claims, psychological explanations, independent algorithm correctness), though it names no alternative tool explicitly.

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