Return the filterable aicoolies catalog index. Equivalent to GET /api/agents/context. Optional category slug, include list, and compact slug-only mode.
| Name | Required | Description | Default |
|---|---|---|---|
| compact | No | If true, return slugs only | |
| include | No | Comma-separated collections: tools,comparisons,reviews,stacks,use_cases,categories,tags | |
| category | No | Category slug, for example ai-native-ides |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It satisfies this reasonably by explicitly mapping the operation to an HTTP GET, which signals a read-only retrieval with no mutation side effects, and by noting compact slug-only and include-list output modes beyond the raw schema.
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 one economical sentence, front-loads the core behavior and endpoint, and then lists the optional modes. Every clause earns its place with no filler.
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, zero-required-parameter read operation, the description covers purpose, endpoint, and output shape modes. The absence of an output schema means a slightly more explicit return-format description could help, but the catalog-index phrasing and compact mode give an agent enough context to call the tool correctly.
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 100%, so the schema already documents all three parameters. The description adds no new semantic detail beyond a brief summary of the optional flags; it doesn't compensate beyond the baseline.
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 identifies a specific verb ('Return') and resource ('filterable aicoolies catalog index'), and anchors it to the exact API endpoint ('GET /api/agents/context'). This makes it easy to tell apart from sibling tools like get_catalog_meta or search_tools, which address different operations.
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 phrase 'filterable catalog index' and the optional parameters imply this is the tool for retrieving a filtered catalog listing, but there is no explicit guidance about when to choose it over siblings such as search_tools or get_catalog_meta, and no exclusion criteria.
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 has a clearly separate role: catalog index vs metadata vs single-tool fetch vs search vs developer resources. Even get_tool and search_tools are distinguishable because one requires an exact slug while the other returns matching records.
All names follow a snake_case verb_noun pattern (get_catalog_context, get_catalog_meta, get_tool, list_developer_resources, search_tools). The verbs correspond to the action, and the naming is predictable across the set.
Five tools is appropriate for a read-only public catalog server. Each tool covers a necessary access pattern (context, metadata, single fetch, search, developer resources) without redundant entries.
The domain is catalog access, and the surface covers the full read path: metadata first, full context, specific tool lookup, search, and developer resources. No obvious write or lifecycle operations are needed for this public catalog use case.