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

Goes well beyond the annotations: shared allowance of 60 per hour with the app including still-running drafts, a rate_limited failure mode, refusal while the account is paused, required actions.write scope plus Agent Picks, and the OAuth/key-creator project management requirement. It also lists the returned fields (draft_id, status, job, requests, building_blocks, competitors, rejected proposals), so the agent knows what success looks like even though there is no output schema.

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?

The core action and the save-it-later constraint are front-loaded, and each subsequent clause carries distinct operational information (contents, rate limit, refusal conditions, auth, return fields). It is dense and runs long for a single paragraph, with some heavy noun stacking around 'built_its_own and no_provider', but nothing is filler.

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 one-parameter mutation with no output schema, the description covers contents produced, persistence semantics, rate-limit interaction, authorization requirements, failure/refusal conditions, and return fields. An agent has everything needed to call it correctly and interpret the result.

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 coverage is 0% for the single optional parameter, so the description has to carry the meaning, and it does: 'job' is the job line and is only supplied 'when job is null', implying it is optional and that a job line is otherwise derived from the project's product. It does not give format, length, or content conventions beyond the schema's maxLength of 300.

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 ('Draft a custom Agent Picks job') and enumerates what the draft contains: requests, building blocks that decide built_its_own and no_provider, competitor suggestions, and the job line. It explicitly distinguishes itself from the save sibling ('nothing reaches a test until devtune_save_agent_picks_job saves it'), so an agent can separate it from devtune_save_agent_picks_job and devtune_draft_agent_picks_tool 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?

Makes the use case clear through the proposal framing and names the follow-up tool that commits the draft, which is the practical 'when to use this vs. that' signal. It stops short of stating explicit exclusions or preconditions for choosing a draft over directly saving a job, but the context is unambiguous.

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