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

Even though annotations already declare readOnlyHint=true and idempotentHint=true, the description goes further by explaining the exact conflict behavior: existing user rules are preserved, and if a covered token already exists the stance version is reported rather than applied. This resolves the apparent risk of a 'merge' mutating the file and matches the annotations with no contradiction.

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 core action is front-loaded and every clause contributes either the stance list, the preservation guarantee, or the report-not-apply behavior. It is a long single sentence, which makes it slightly denser than ideal, but there is no filler or repetition.

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 two-parameter tool with high schema coverage and safety annotations, the description covers the main prerequisite (existing robots.txt) and the non-destructive outcome. It does not describe the exact report/output format, and no output schema exists to fill that gap, so a small completeness gap remains.

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 coverage is 100% and both parameter descriptions are already meaningful, so the baseline is 3. The description adds value by listing all eight accepted stance slugs and clarifying that robots_txt is an existing file to be augmented, which is especially helpful because the schema has no enum constraint.

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 opens with a specific verb and resource ('Merge ... robots.txt stances into a robots.txt you already have') and enumerates the exact eight stances, so the agent knows precisely what action is offered. It also asserts a key constraint ('without touching a single rule you wrote'), which distinguishes this policy-merging tool from the sibling audit/lint/diff/check tools.

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 phrase 'robots.txt you already have' implies this is for augmenting an existing file rather than creating one, so usage context is only implied. The description does not name sibling tools, state when not to use merge_policy, or explain why audit_ai_access/check_path_allowed/diff_robots_txt/lint_robots_txt would be alternatives.

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