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

Goes well beyond the annotations by disclosing that scheduling is asynchronous, that scheduling is not completion, and the expected wait before re-reading. It also sets expectations about interpretation ('a passing check is an observation, not compatibility or store approval'). The readOnlyHint=false is consistent with a tool that can enqueue work, but the description never clarifies what the check actually validates or what state a scheduled check leaves behind.

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-loads the read-vs-build distinction, then the scheduling procedure, then the interpretation caveat — a sensible order with no filler. Some sentences are telegraphic fragments ('If not scheduled, say so and use the portal') whose reference to 'the portal' is never defined, costing a little clarity.

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 two-parameter tool with no output schema, the description adequately covers modes, the sequencing between call and re-read, and the limits of the result's meaning. Minor gaps remain: what fields other than health_checked_at come back and whether the one-minute wait is a fixed rule or an estimate.

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 100% and the run parameter's schema description already covers the asynchronous scheduling and 'do not infer completion' semantics, so the description largely restates structured data. It adds only the follow-up timing ('re-read without run after a minute'), leaving project_code meaning entirely to the schema. Baseline 3 is appropriate.

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 health checks and health_checked_at') and explicitly excludes a confusable adjacent concept ('not build execution status'), which routes the agent away from bdk_build. It also names the secondary mode ('run:true schedules an asynchronous check'), so the dual read/schedule nature of bdk_check is unambiguous.

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 branches: schedule with run:true, then re-read without run after a minute rather than polling or inferring. It also names the fallback when nothing is scheduled ('say so and use the portal'), which is a concrete alternative path rather than an implied one.

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