fetchFetch the full document for one search result by its opaque id (project: or listing:). Returns { id, title, text, url, metadata }. Available without a token; public data only. Wraps projects_get_deep_dive and marketplace_listing_get. Unknown or malformed ids return a clean not-found.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| url | Yes | ||
| text | Yes | ||
| title | Yes | ||
| metadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses return fields, authentication (public data), internal endpoint wrapping, and error handling for unknown IDs. Lacks rate limits, but as a read-only fetch this is acceptable.
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?
Every sentence provides value: purpose, id format, return shape, auth, internal wrapping, error behavior. No wasted words, front-loaded with the action.
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 simple one-parameter tool with no annotations, the description covers input, output, auth, and edge cases. Output schema exists but is not needed since return is described. Complete for correct tool selection.
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?
Despite 0% schema coverage, the description adds meaning by specifying the id format ('project:<uuid> or listing:<uuid>') and its source. This is essential context beyond the schema's generic string type.
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 the verb 'Fetch' and the resource 'full document for one search result by its opaque id'. It distinguishes from sibling search tools which return summaries, making its purpose unique.
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 states when to use (have an opaque id from search) and that it's public (no token needed). Implicitly guides away from search tools, but doesn't explicitly mention alternatives for when not to use.
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.
The search tools (search, projects_search, marketplace_listings_search) overlap significantly—search is explicitly an 'additive alias' over the other two, making them partially redundant. fetch, getting_started, and marketplace_listings_search are fairly distinct, but the search trio creates ambiguity about which to call for a given query.
Mixed conventions: projects_search and marketplace_listings_search follow verb_noun, but search, fetch, and getting_started are single words/varied patterns. Names are descriptive enough but lack a uniform verb_noun structure across the whole set.
Five tools is a reasonable size for a search/discovery-oriented server. The count feels slightly thin given the mention of several underlying operations (projects_get_deep_dive, marketplace_listing_get), but it's within a sensible scope for the apparent purpose.
Read-side coverage is decent: search, detail-fetch, and overview docs are all present. However, the server references get_deep_dive and get operations that aren't directly exposed as standalone tools, and there's no way to perform any writes/updates, leaving the surface feel like incomplete proxies for a broader API.