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

Annotations already provide readOnlyHint=true and destructiveHint=false, and the description restates 'Read-only' and 'without changing it' — which is redundant but not harmful. The description does add that it 'returns the generation by numeric generation_id', a small behavioral detail (the return object is the generation), but no extra side effects, permissions, or limits are disclosed beyond what the annotations already imply. With annotations carrying the safety profile, the additional value here is minor.

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 efficiently worded in two sentences totaling less than 50 words. The first sentence front-loads the primary usage cases; the second adds the read-only guarantee. It is slightly redundant with the annotations ('read-only', 'without changing it'), but that redundancy is short and does not distract. No fluff; each clause serves the task.

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?

For a tool with no output schema, the description gives only a high-level return ('returns the generation') and says it includes 'generated markdown' and 'version metadata' in the trigger context. It does not fully specify the return shape (e.g., which fields of the generation object are returned), nor does it mention pagination or any error conditions. Given the tool's simplicity and full schema coverage, this is adequate but leaves the exact response payload partially unexplained, which matters because there is no output schema to fill the gap.

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?

The schema description coverage is 100%: generation_id is described as 'The numeric generation ID. Call list-generations first' and include_source as 'Include the original source code/content. Defaults to false.' The description adds a phrase 'inspect version metadata, see generated markdown' which loosely hints at what include_source might affect, but it does not go beyond the schema's explicit parameter descriptions. Baseline 3 applies because the schema already does the heavy lifting.

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 uses a specific verb 'read' and a specific resource ('a specific generated output/result', 'generation'). It distinguishes this tool from siblings like list-generations (listing) and update-generation (mutating) by emphasizing a single read-only fetch — 'read a specific generated output', 'returns the generation by numeric generation_id' — and by naming the target. The scope and intent are unambiguous.

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 explicitly states the conditions for use: 'when the user wants to read a specific generated output, inspect version metadata, see generated markdown, or choose a version for later actions'. This provides a clear trigger context. However, it does not explicitly mention alternatives like list-generations or say 'not for listing' or 'not for updating', so exclusions are absent. The usage context is strong but lacks direct contrast with related tools.

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