architect_language_repair

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

Annotations only give generic hints (readOnly=false, destructive=false, idempotent=false); the description adds real semantics: facts and live files are preserved, there is a hard two-attempt cap per document lineage, and the output is a candidate requiring review. These are behavioral facts not derivable from annotations. It stops short of saying what is written or where the candidate lands.

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, then invariants, then the follow-up step. No filler. Slight density from unexplained jargon but nothing extraneous.

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 mutation-style tool in a multi-step grant/workflow pipeline with no output schema and 6 of 7 parameters undocumented. The description covers intent and guardrails but leaves an agent unable to know what expected_snapshot must match, what skill to pass, or what a successful proposal returns.

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 14% (only `workspace` documented) across 7 parameters, so the description must compensate and it does not. Six required parameters — text, skill, change_id, artifact_id, expected_snapshot — are completely unexplained; 'accepted grant' weakly implies change_id/artifact_id but expected_snapshot and operation_id remain opaque.

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+resource: 'Propose a targeted host-authored repair under an accepted grant.' The closing 'Candidate still needs review' implicitly separates it from architect_candidate_review / architect_language_review, but the distinction is only suggested, not stated, and 'host-authored repair' is jargon an agent must already understand from the domain.

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?

Preconditions are implied ('under an accepted grant', 'at most two repair attempts per document lineage'), which tells the agent when the tool is legal, but it never names the sibling that creates the grant or the review tool to call afterwards. No explicit when-not or alternative routing.

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