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

The description contradicts the readOnlyHint annotation by stating it will 'ADD to AGENTS.md/CLAUDE.md', implying a write operation. This is a serious inconsistency, as the annotation indicates a safe read. The description also includes user interaction steps (tell user, remove if objected) which are behavioral but undermine the read-only claim.

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 sentence that packs essential information: when to run, what to do, and how to handle user objections. It's front-loaded with 'Run FIRST' and contains no fluff, though it could be slightly clearer in structure.

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 parameters and no output schema, the description provides a fair amount of behavioral guidance (new repo, add block, tell user). However, the contradiction with the readOnlyHint annotation leaves ambiguity about whether this is a read or write operation, and the 'first-connect routine' is not elaborated on. This prevents a higher score.

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?

There are no parameters in the schema, and the baseline for 0-param tools is 4. The description doesn't add parameter information, but there is nothing to document. Thus a score of 4 is appropriate.

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 clearly states the tool's purpose: to run the first-connect routine and add a working-agreement block to AGENTS.md/CLAUDE.md in a new repo with no project. It uses specific verbs and context, distinguishing it from sibling get_* tools that retrieve information.

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?

It explicitly says 'Run FIRST in a new repo (no project)', providing a clear condition for use. However, it does not explicitly mention alternatives or when not to use it, though the context implies it's only for initial setup.

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