Preview mechanical validation fixes

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

Beyond the readOnlyHint annotation, the description details that the tool only returns a change set (no auto-apply), fails closed on empty results or large scale, and distinguishes its scope from object deletion. No contradiction with annotations.

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 well-structured sentences with no fluff, each serving a distinct purpose: action, differentiation, and edge-case handling. Slightly dense but efficient.

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?

Given the tool's complexity (3 required params, output schema present), the description covers its purpose, limitations, failure modes, and relationship to siblings. An agent has sufficient context to decide when and how to invoke it.

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 provides descriptions for 2 of 3 parameters; the description does not add significant parameter-specific meaning beyond implying the revision parameters ensure concurrency. The overall context aids interpretation but does not deeply enrich individual param understanding.

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 precisely states the tool scans tile layers for dangling GID cells and returns a change set to erase them. It distinguishes from siblings like tiled_validate by explicitly noting which issues it fixes and which it does not (tile-object GIDs).

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?

The description clearly indicates when to use (for fixing dangling cells) and when not (for tile-object GIDs, large scale >10k cells suggests broken reference). It references tiled_validate as the alternative for reporting.

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