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

With no annotations at all, the description carries real weight: it names the concrete endpoint (POST /v2/jobs/{id}/submit), warns that job text is data rather than instructions (prompt-injection guard), and states the wallet is a payout address only with no key handling. It does not disclose idempotency, whether a submission is final, or what happens on validation failure.

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 action, then the payload contract, then safety constraints — good ordering with no filler sentences. The raw HTTP method and URL are somewhat implementation-level for an MCP caller, but they anchor the versioning distinction.

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 dual-version submission tool with no annotations and no output schema, the description covers the payload contract, the prerequisite lookup tool, and security boundaries. The remaining gap is the return behavior — nothing says what a successful submission yields or how submission_status relates to it.

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 context signal reports 0% schema coverage, so the description must compensate, and it largely does: it gives a full worked JSON body showing the wallet and the four item fields, and explains that extra keys are passed through for v1 jobs. It does not explain accepted value formats for item_id/outcome_id beyond what get_job returns.

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 ("Submit work for a job") and immediately disambiguates the two payload shapes: v2 items[] with item_id/outcome_id/answer/evidence versus v1 code or job-specific items. An agent can tell exactly which input form applies without opening the 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?

It points at the prerequisite sibling by name — get_job returns submit_url, input_url and the exact answer/evidence schemas — which tells the agent to fetch job context before submitting. It stops short of explicit exclusions, e.g. it never says what to do about re-submission or how this relates to submission_status.

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