itemFetch a single Guardian article by its content ID (e.g. "world/2024/jan/15/..."). Returns full body text, tags, related elements, and references. Use after search returns an article you want the full text of.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| show_tags | No | ||
| show_blocks | No | ||
| show_fields | No | ||
| show_references | No |
| Name | Required | Description | Default |
|---|---|---|---|
| response | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds value by detailing what is returned (full body text, tags, related elements, references), which is not in the schema. No contradictions.
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?
Two sentences, front-loaded with action and parameter, then usage context. No extraneous words, every sentence provides value.
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?
With an output schema present, return value details are less critical. Annotations cover safety. However, the description fails to explain four optional parameters, which is a significant gap. Completeness is adequate for a simple fetch tool but not fully informative.
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 explain parameters. It only mentions 'content ID' in text, leaving show_tags, show_blocks, show_fields, and show_references unexplained. The schema examples provide some context, but the description doesn't compensate for the lack of schema descriptions. Agent would not know the meaning or values of optional parameters.
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 it fetches a single article by content ID and lists returned data (full body text, tags, etc.). It distinguishes from sibling 'search' by specifying usage after a search. Very clear verb+resource+scope.
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 says 'Use after search returns an article you want the full text of', providing clear context. No explicit when-not or alternatives beyond search, but enough guidance for typical 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.
Many tools have overlapping purposes and similar names, especially the Pipeworx query tools (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) and the Polymarket tools (polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, etc.). The Guardian-specific tools are distinct but are outnumbered by these confusing clusters, making it hard for an agent to reliably select the right tool.
Tool names follow no consistent pattern: some are snake_case (ai_visibility_check, ask_pipeworx), some are verbs without objects (item, tags, forget, recall), and some are inconsistent in style (compare_entities vs. bet_research). There is no unifying naming convention across the set.
With 36 tools, the server is bloated for its implied purpose ('The Guardian' suggests a focused news outlet). Many tools belong to unrelated domains (Pipeworx data platform, Polymarket prediction markets), making the count feel excessive and unfocused. A news-specific server should have far fewer tools.
The tool set lacks a coherent domain. The Guardian news tools are complete (search, item, sections, etc.), but the massive inclusion of Pipeworx and Polymarket tools creates dead ends and gaps (e.g., no direct tool to list all prediction markets or search patents). The surface feels like a random collection rather than a designed whole.