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

Annotations already cover readOnlyHint, destructiveHint, and openWorldHint, so the safety profile is known. The description adds only the pre-save/pre-publish timing; it does not explain diff behavior, scope semantics, path limits, pagination, or output shape, leaving significant behavioral context unstated.

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 description is a single front-loaded clause with no wasted words. However, its extreme terseness leaves no room for essential structure or caller guidance, so it is concise but underpowered for a seven-parameter tool.

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?

The tool has seven parameters, zero schema description coverage, no output schema, and only sparse annotations. The one-line description is not complete enough to tell an agent how to invoke it correctly or interpret the results.

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%, and the description mentions no parameters at all. It does not explain the required workspace/build_id, the paths limit, the scope enum, cursor pagination, format values, or context_lines, so it fails to compensate for the missing schema descriptions.

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 phrase 'Source differences before save/publish' indicates a diff-like operation and adds timing context, but it does not state the specific resource being compared or name the relevant build files. It is clearer than a tautology but does not distinguish itself from siblings such as references_compare or builds_validate.

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?

'Before save/publish' implies a workflow context, giving some guidance about when to call it. However, there are no explicit alternatives, exclusions, or prerequisites, so the agent must infer when to use this versus files_read, references_compare, or builds_validate.

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