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

Annotations declare a non-read-only, open-world, non-idempotent, non-destructive write, and the description is consistent while adding material context they cannot carry: a shared 60-an-hour draft allowance with rate_limited signalling, refusal while the account is paused, the required actions.write scope plus Agent Picks, and the project-management rights needed by the OAuth member or API-key creator. It also enumerates the response fields (draft_id, status, tool_key, signals, relationships, sources, rejected, failure) and constrains relationship provenance to the drafted tool's own site, never registry text.

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 purpose is front-loaded, but the body is a dense run of long sentences that mix parameter guidance, return fields, relationship semantics, follow-up steps, rate limits, and permissions without structure. The relationship explanation in particular ('yields to yields_to, the drafted tool, so a run that uses both counts as yields_to') takes several passes to parse and could be split or bulleted.

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 five-parameter drafting tool with no output schema and no schema descriptions, the definition still covers inputs, return fields, error/refusal conditions, quota behavior, authorization requirements, and what to do with the output. An agent could call it and consume the result without consulting anything else.

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 0%, so the description carries the full burden and largely does: it identifies tool_key, name, domain (explicitly nullable), the job line, and other_tools as tool_key/name pairs of the job's other tools used to propose intra-run containment. It does not cover the schema's bounds such as other_tools maxItems 35 or field length limits, so it adds meaning but not full coverage.

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 one tool's signals for a custom Agent Picks job, sourced from package registries and the tool's own site. The enumerated signal types (packages, config names, import patterns, config files, config patterns, domains) and the phrase 'one tool's signals' distinguish it from the sibling devtune_draft_agent_picks_job, which drafts the job itself.

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 call guidance (pass tool_key, name, domain or null, the job line, and other_tools) and a downstream step: apply a relationship by adding yields_to to that tool's signals.yieldsTo, then pass signals and draft_id to devtune_save_agent_picks_job. It also names exclusions (refused while paused, rate_limited when the shared 60/hour allowance is spent). It never explicitly states when to prefer this over devtune_draft_agent_picks_job, leaving that ordering inferable rather than stated.

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