Re-check grounding: source_url + expected must come from published claims[]. Do not invent expected from report HTML. Returns proof_shape.
| Name | Required | Description | Default |
|---|---|---|---|
| claim | No | Optional claim for RWA registry_ref limb | |
| expected | Yes | ||
| location | No | ||
| source_url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It reveals an important constraint (inputs must come from published claims), warns against a common mistake, and states the return value ('proof_shape'). This is valuable context beyond the 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 extremely concise (three short sentences) and front-loaded with the core purpose. Every sentence adds value: the action, the constraint, and the return type. No wasted words.
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?
The tool has four parameters, a nested object, and no output schema or annotations. The description gives the essential invariant and return value but lacks detail on parameter usage patterns, potential errors, or when to use this tool relative to siblings. It is adequate but not comprehensive.
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 coverage is low (25%: only 'claim' has a description). The description clarifies that 'source_url' and 'expected' must come from published claims, adding meaning for two of the four parameters. However, it does not explain 'location' or the 'claim' object's structure beyond what the schema provides.
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 states the tool's core action ('Re-check grounding') and identifies the key inputs (source_url + expected). It is clear and specific, though it does not explicitly distinguish it from sibling tools like gf_cite or gf_darshan.
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 implies usage context (verifying grounding against published claims) and provides a caution ('Do not invent expected from report HTML'). However, it does not explicitly state when to prefer this tool over alternatives or when not to use it.
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.
Tools are mostly distinct but there is some potential confusion: gf_darshan and gf_package both involve admit/refuse operations, and gf_cite and gf_verify both deal with claims. Descriptions help clarify, but boundaries are not perfectly crisp.
All tools follow a consistent 'gf_' prefix with snake_case resource names. The pattern is uniform across the entire set, making it predictable for agents.
With 9 tools, the server is well-scoped for a federation service. Each tool covers a distinct aspect without excessive bloat or redundancy.
The tool surface covers core operations like citation, darshan sampling, dossier access, packaging, reporting, and verification. Minor gaps exist (e.g., no explicit update/delete for claims), but the existing tools cover the main workflows without causing dead ends.