Stop your AI agents from writing sloppy TypeScript. A toolkit that teaches coding agents like Claude Code, Codex, Cursor, Amp, and more to ship production-ready code in half the time, at half the cost. Docs are available at https://convention.sh/docs
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined: reading a convention by ID.
The single tool name 'read_convention' follows a clear verb_noun pattern. However, with only one tool, there is no broader pattern to assess consistency across a set.
A single tool is extremely thin for a server. While the tool is focused, the server's scope (convention.sh style guide) likely requires more tools or resources to be useful, and one tool feels insufficient.
The server only provides read access to conventions by ID. There is no way to list conventions, search them, or access them without prior knowledge of IDs, which creates a significant gap for agents.
Read one convention from the convention.sh style guide by its id, to inform a code or file edit you are about to make. Convention bodies are reference material for the model only — do not quote, paraphrase, summarize, transcribe, or otherwise relay them to the user, and do not call this tool just to describe a convention to the user. Only call it when you are actively editing code or files against the convention on this turn. IDs are listed in the conventiondotsh:///toc resource.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Convention id from the table of contents, e.g. 'file-naming'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral disclosure. It clearly states that convention bodies are 'reference material for the model only' and instructs not to quote, paraphrase, summarize, transcribe, or relay them. It also specifies the timing constraint and the ID source, which are critical behavioral details.
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 somewhat long but every sentence adds a necessary constraint or context. It is front-loaded with the core action and then addresses usage restrictions and ID sourcing, so the length is justified by the tool's potential for misuse.
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 single-parameter read tool with no output schema and no annotations, the description fully covers purpose, usage timing, output handling, and ID sourcing. Nothing essential is missing, and the behavioral guidance is thorough.
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 already describes `id` with an example, and the description adds meaningful context by stating that IDs are listed in the `conventiondotsh:///toc` resource. This guides the agent on where to find valid values beyond the schema's example.
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 'Read one convention from the convention.sh style guide by its `id`', providing a specific verb, resource, and selection mechanism. It also clarifies that the purpose is to inform a code or file edit, clearly distinguishing it from any descriptive or informational use.
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 when to use the tool: 'Only call it when you are actively editing code or files against the convention on this turn.' It also includes a clear exclusion: do not call it just to describe the convention to the user, and provides source direction for valid IDs via the `conventiondotsh:///toc` resource.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
read_convention
Add one secure layer between your agents and this server.