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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real behavioral context: default server-side execution on Cloudflare Workers, compute:'browser' returning a delegation URL, gpu:true always delegating, transient non-retained input processing, and export of an AP2 artifact with execution_hash for provenance. This meaningfully exceeds what the annotations convey.

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?

It is front-loaded with the identity and compute behavior, which are the useful parts, but the block also carries template cruft (full URL, FV-status receipt sentence) that dilutes the signal. The 'not stored, logged, or retained' clause earns its place; the trailing snapshot explanation does not.

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 and full annotations exist, so return values and safety need not be re-explained, and the description covers compute modes, provenance, and chaining. What is missing is the substantive purpose of the scoring function itself, leaving an agent able to invoke it mechanically but not to reason about when it is the right tool.

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% and every parameter is documented, including the compute enum and the parent_hashes/parent_tool_ids ordering constraint, so the schema does the heavy lifting. The description reinforces the compute-mode semantics but adds no syntax or format detail beyond the schema, warranting the baseline 3.

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 opens by restating the name ('Arc Partner Stablecoin Onboarding Conformance') and labels it a 'compute node (compliance_mandate)', which gives a general sense of a conformance-scoring node but never states what it actually scores or what its decision function evaluates. Siblings like route_partner_stablecoin_jurisdiction and lint_arc_xreserve_config are not differentiated. Purpose is implied, not specified.

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?

It provides pipeline context ('Consumes upstream artifacts from: art-42-arc-fit-diagnostic. Output feeds: art-45-arc-xreserve-linter') and a data-handling constraint ('Use synthetic or anonymised inputs only'), which is genuinely useful. However there is no explicit when-to-use vs alternative guidance and no statement of preconditions for the chaining.

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