List every data source in the corpus with its license, homepage, narrative count, and republication policy (full vs excerpt).
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | every source in the corpus |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool read-only, idempotent, and non-destructive; the description adds concrete behavioral context by stating the unfiltered scope ('every data source') and the exact fields returned. This exceeds what annotations alone convey, though it omits richer details such as pagination or data freshness, which are partly covered by the existing output 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?
A single well-structured sentence front-loads the action and scope, then packs the response fields into a compact clause. There is no redundant or filler content.
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 zero-parameter, read-only list tool with an output schema, the description provides all essential context: scope, returned attributes, and the full-vs-excerpt nuance. Nothing needed for correct invocation is missing.
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?
With zero parameters, there is no parameter burden for the description to carry; the baseline of 4 applies. The schema coverage is complete, and the description's field list compensates for any ambiguity about what the empty-schema listing returns.
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 names a concrete action ('List every data source in the corpus') and enumerates the output attributes (license, homepage, narrative count, republication policy), making the tool's purpose unmistakable. It is naturally distinguished from the sibling accident/lookup tools, which are specific records rather than corpus metadata.
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 clearly implies this is the go-to for a corpus-level inventory, but it does not explicitly state when to use it versus alternatives or mention any exclusions. Usage context is inferable from the zero-parameter design and sibling names, not stated.
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 maps to a distinct resource or dataset: accidents, narratives, sources, airport references, and the three FAA summary datasets. Even the get/search accident pair is clearly split by retrieve-by-ID versus filtered-search, so an agent should not struggle to pick the right tool.
All names use snake_case and are readable, with noun-style dataset tools like wildlife_strikes and laser_incidents alongside verb-prefixed actions like search_accidents and list_sources. This is a minor deviation from a strict verb_noun convention, but it remains predictable.
Nine tools is appropriate for a safety-data server that spans an accident corpus, narratives, source metadata, airport lookups, and multiple FAA datasets. Each tool earns its place and there is no obvious bloat or thinness.
The surface covers accident search/retrieval, narrative access, source metadata, airport resolution, and three FAA summary datasets. Notable gaps are the lack of occurrence-level retrieval for drone/laser/wildlife events and no explicit slug/autocomplete endpoint for aircraft families, but agents can usually work around these.