Submit optional research interest or skill feedback. Use a random pseudonym; omit private scenarios, names, contact details and credentials. No order or payment. Raw feedback retained 30 days.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| model | Yes | ||
| budget | Yes | ||
| domain | Yes | ||
| rating | No | ||
| comment | No | ||
| client_id | Yes | ||
| human_confirmed | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden and does meaningful work: it states retention ('Raw feedback retained 30 days'), confirms this is not a commercial transaction ('No order or payment'), and imposes privacy expectations. It could add what happens after submission, but the disclosed traits are substantive.
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 four short, front-loaded sentences with no filler. Every sentence contributes: purpose, privacy requirements, exclusion of order/payment, and retention.
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?
The privacy and retention context is well covered, but for a tool with 8 parameters, 5 required, and no annotations or output schema, the description is only minimally complete. It does not explain the required identifiers or budget/model fields, although the enum values reduce some ambiguity.
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 description coverage is 0%, so the description must compensate; it only hints at the 'kind' parameter via 'research interest or skill feedback' and leaves client_id, model, budget, rating, comment, human_confirmed, and domain semantically unexplained. The enums are self-explanatory, but the description itself adds little parameter-level meaning.
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 action-resource pair: 'Submit optional research interest or skill feedback,' and the two feedback kinds map to the schema's kind enum. It does not explicitly differentiate from sibling tools such as research_preview, so it falls short of a 5.
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 gives clear how-to-use guidance (use a pseudonym, omit private data) and states this is not for order or payment, but it never says when to choose this tool over alternatives. No sibling is named and there is no explicit when-to-use / when-not-to-use framing beyond the implied feedback context.
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.
Each tool targets a distinct resource: catalog lists available items, kit_catalog previews unevaluated kits, method reads free methods, pack_offer returns payable URLs, and research_feedback is the only write action. However, catalog vs kit_catalog and the preview-style tools (kit_catalog, research_preview) have close enough names/functions to cause occasional misselection.
All tool names follow the same lowercase snake_case noun-phrase convention, such as catalog, kit_catalog, pack_offer, and research_preview. There is no mixing of styles or inconsistent verb usage.
Seven tools is well-scoped for a knowledge-commons server covering catalogs, free content, paid offers, previews, samples, and feedback. Each tool has a clear purpose and none feel redundant.
Core workflows are covered: browse catalogs, read free methods, obtain payable pack URLs, preview research, fetch a sample pack, and submit feedback. There is no explicit decision-pack content reader or purchase tool, but pack_offer intentionally stops at the payable URL, suggesting a deliberate boundary rather than a dead end.