Review a HeyClaude submission draft locally for schema errors, duplicate risk, and maintainer checklist items without writing to GitHub.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | Submission field values to review for schema errors and maintainer checklist items. | |
| duplicateLimit | No | Maximum number of duplicate candidates to include in the review. |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| policy | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint. Description adds that the tool checks schema errors, duplicate risk, and maintainer checklist items, plus emphasizes local-only operation (no GitHub write). This is useful context beyond annotations.
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?
Single sentence of 20 words, front-loaded with action and scope. Every word is necessary; no redundancy.
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 a large nested input schema and an output schema, the description covers the overall purpose and key checks. It doesn't detail output format, but since output schema exists, it's acceptable. A brief mention of the output type would push to 5.
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 descriptions already explain 'fields' and 'duplicateLimit'. The description only restates the schema's purpose (schema errors, duplicate risk, checklist) without adding new semantic detail. Baseline 3 applies.
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?
Description clearly states it reviews a submission draft locally for schema errors, duplicate risk, and maintainer checklist items, avoiding GitHub writes. This distinguishes it from siblings like submission.validate and submission.prepare.
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?
Explicitly notes it works locally without writing to GitHub, providing clear context. However, it doesn't explicitly state when to use this combined review over individual sibling tools for each aspect (e.g., submission.duplicates, submission.validate).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, especially with clear prefixes. However, there is some overlap between entry.safety and entry.trust (both deal with safety/trust metadata), and between registry.recommend and registry.plan (both provide recommendations). The descriptions help differentiate but some ambiguity remains.
All tool names follow a consistent pattern: a domain prefix (entry, install, registry, submission) followed by a descriptive noun, all lowercase with underscores. This makes the surface predictable and easy to navigate.
27 tools is slightly high but reasonable given the broad scope of the HeyClaude registry, which includes browsing, recommending, installing guidance, and submission preparation. The count is appropriate for the server's purpose.
The tool surface is comprehensive, covering search, detail, comparison, safety/trust analysis, install setup for multiple clients, recommendation, and a full submission pipeline (validation, review, schema, etc.). There are no obvious gaps for the intended read-only registry directory functionality.
