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

Annotations already cover the read-only, idempotent, non-destructive profile, but the description adds context they do not carry: no charge is incurred, a bearer key is required, and the two failure modes (WORKSPACE_KEY_REQUIRED, NOT_FOUND) are named. That is real behavioral disclosure beyond the structured hints.

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?

Six short clauses, front-loaded with identity and scope, then usage, then prerequisites, then return and error shape. No sentence is redundant and nothing is buried.

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 single-parameter read tool with an output schema, this covers everything the agent needs: purpose, exclusions, sequencing against siblings, auth requirement, and error surface. Return-value explanation is technically redundant given the output schema but costs little.

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 the single job_id parameter is already fully documented in the schema (including the hosted-MCP requirement). The description's 'Hosted MCP accepts job_id only' largely restates that field description, so it meets the baseline without adding new syntax or format detail.

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 ('Read billing and provenance for a finished job') and immediately delimits scope with 'Does not run capabilities or spend money', separating it from hydracept_run and hydracept_quote_capability. The agent can distinguish this from every sibling without opening a schema.

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 explicit when-to-use ('after terminal success') and an explicit alternative with its own trigger condition ('use hydracept_job_status while still running'). It also pre-empts the hosted-MCP parameter constraint and the bearer-key prerequisite.

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