submit_shape_repair_candidate

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

With no annotations, the description carries the full disclosure burden and does supply useful behavior: staging is immutable, gates run before anything is queued, and validation/evidence is queued asynchronously rather than resolved inline. It omits what happens on a SHA-256 mismatch, whether resubmission with the same idempotency_key is safe, and what identifiers come back from the queued job.

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?

Three short sentences, front-loaded with the action and followed by prerequisites and the negative scope. No filler or restatement of the tool name. Slightly compressed to the point that a few clause fragments ('an explicit region') read as terse notes rather than prose.

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?

This is a high-complexity mutation with 11 parameters, 8 required, a nested recipe object, no annotations, and no output schema. The description should therefore explain the return shape (a queued validation job id?), failure modes such as hash mismatch or path outside allowed roots, and idempotency behavior, none of which are 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 description coverage is 0% across 11 parameters, so the description must compensate and largely does not. It explains only the recipe.method constraint and the two hash fields (and references a 'region' that does not appear as a top-level property), leaving batch_id, asset_id, candidate_path, source_attempt, inspected_paths, expected_shape_attempt, idempotency_key, and diagnosis entirely undocumented.

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?

The description names a specific action and object: staging an allowed-root edited GLB immutably and running the repair gates on it. That is clearly a submission/validation-queue operation, not a generation or status tool, so it is distinguishable from most siblings. It stops short of naming create_shape_repair_attempt, the closest sibling, so the boundary between the two is left implicit.

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?

Prerequisites are stated concretely (recipe.method=import_candidate, an explicit region, exact candidate/source SHA-256 values), which tells the agent when the call is legal. The line 'it does not accept the candidate' signals a boundary, but no alternative tool is named for the acceptance step, and no guidance distinguishes this from create_shape_repair_attempt.

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