get_storyFetch a single story by its id, including every source that reported it. Story ids are permanent — a published story keeps its id and its public URL indefinitely — so they are safe to store.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | the story's `id`, as returned by search_news |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes that this is a safe read operation. The description goes further by disclosing that the response includes every source for the story, and that story IDs and public URLs are permanent, making IDs safe to store. These are genuinely useful behavioral details beyond the annotations, with no contradiction.
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 two sentences: the first front-loads the action and scope, the second adds valuable durability information. Every sentence earns its place, and there is no redundant 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 one-parameter, read-only lookup tool with no output schema, the definition is complete enough. It specifies what is returned (a story plus all sources), how the id is obtained (schema reference to search_news), and why the id is safe to persist. An agent has what it needs to select and invoke 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?
The input schema already documents the single id parameter thoroughly, including its source ('as returned by search_news'), type, and length constraints. With 100% schema description coverage, the description does not need to add parameter-level detail, and it does not add any beyond the schema.
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 clearly states a specific verb ('Fetch'), a specific resource ('a single story'), and the key qualifier ('by its id'). It also clarifies that the result includes every source that reported it, which distinguishes this from sibling tools like search_news or list_sources that return different shapes.
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 intended usage is clear: fetch a single story when you have its id. The schema's hint that the id comes from search_news reinforces the workflow, and the mention of permanent IDs adds useful guidance about storing and reusing IDs. However, there is no explicit comparison to alternatives or a direct statement of when not to use this tool.
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 generally distinct purpose, but get_market_summary includes a current price table that overlaps with get_carbon_prices. The descriptions mitigate this by clarifying that get_market_summary is for orientation while get_carbon_prices provides detailed price data from two non-comparable sources.
All tool names follow a consistent verb_noun pattern in snake_case: get_carbon_prices, get_market_summary, get_price_history, get_story, list_sources, and search_news. The naming is predictable and clearly indicates the returned resource.
Six tools is a well-scoped size for a carbon market data and news retrieval server. Each tool covers a distinct need without unnecessary redundancy or bloat.
The tool surface covers the core read-only workflows: current prices, historical prices, market orientation, news search, story retrieval by id, and source coverage discovery. The workflows connect naturally, e.g., get_market_summary provides tags for search_news, and search_news results can be followed by get_story.