check_seal

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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent), and the description adds genuinely new context: the possible 'indeterminate' outcome, that unsupported sealing geometry degrades confidence, and that an annotated image plus a compartment report is produced. It does not discuss cost, limits, or what 'seeds' fallback behavior means when omitted, which keeps it below the top mark.

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 and mechanism come first, followed by usage timing, caveats, and return shape, in four tight sentences with no filler. Every sentence carries distinct information.

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?

With no output schema, the description correctly discloses the return value (image with highlighted escape path and a connected-compartment report). For a three-parameter read-only check, purpose, trigger, caveat, and output are all present.

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%, so design, seeds and door_state are already fully documented in the schema, including the enum-like closed/open values and the imported-vs-generated seeds rule. The description adds nothing parameter-specific beyond what the schema provides, so the baseline 3 applies.

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 — testing whether a draft is watertight — and describes the mechanism (tracing from interior points to the outside) plus the tri-state result per compartment. This is clearly distinguishable from nearby siblings like analyze_hull or preview_hull, which imply different operations.

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?

'Use it after edits that touch the hull or doors' gives a clear triggering condition, and the note about unsupported sealing geometry warns when a confident pass is impossible. It stops short of naming an alternative tool to use instead when geometry is unsupported, so it is not a full when/when-not/alternative statement.

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