public-evidence_get_document_changesCompare a document with its prior snapshot. Citation locators are source-provided, position-based h2/h3 ID fragments and are valid only within the snapshot that produced them. An upstream heading insertion can shift later locators and make one source edit appear as many changes.
| Name | Required | Description | Default |
|---|---|---|---|
| as_of | No | ||
| document_id | Yes | ||
| snapshot_id | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already indicates a read-only operation. The description adds transparency about a critical behavioral aspect: citation locators are only valid within the snapshot that produced them, and upstream heading insertions can make one edit appear as many changes. This goes beyond the annotation to warn about data interpretation.
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 highly concise: two sentences that front-load the main purpose and then add a relevant caveat. No fluff or redundant information. Every sentence adds 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?
The tool lacks an output schema, and the description does not specify the format or structure of the returned changes (e.g., list of differences with locators). It does provide a helpful caveat about locator validity, but for a tool that returns diff-like data, the absence of any return-type description leaves a notable gap in context.
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% – the description does not explain any of the three parameters (document_id, snapshot_id, as_of). While the names are somewhat self-explanatory, the relationship and precedence between snapshot_id and as_of (e.g., which takes priority) is not addressed. The description does not compensate for the lack of parameter documentation.
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 the tool's purpose: 'Compare a document with its prior snapshot.' It uses a specific verb (compare) and resource (document changes), distinguishing it from sibling tools like public-evidence_get_document (fetch document) and public-evidence_search_passages (search passages). No ambiguity.
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 when to use the tool (to see changes between a document and its snapshot) and provides crucial context about snapshot-relative citation locators and the impact of heading insertions. It does not explicitly name alternatives or state 'use this for X instead of Y', but the purpose is clear enough and the caveat helps interpret results correctly.
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.
Every tool has a unique purpose, and the descriptions are detailed enough to clearly distinguish between search, list, get, and specific operations across domains. No two tools overlap in function.
Domain tools follow a consistent '<domain>_<verb>_<noun>' pattern, but gateway-level tools like 'call_tool', 'find_capability', 'inspect_tool', 'search_services', and 'status' lack the prefix, introducing a minor inconsistency. Overall still readable and predictable.
With 35 tools, the count exceeds the typical 3–15 range, but this is a gateway aggregating multiple distinct domains (holidays, laws, opendata, recalls, etc.), making the larger set justified. The count feels appropriate for the server's purpose.
Each domain offers a full set of operations: search, list, get, and domain-specific actions (like count_business_days or get_document_changes). Gateway meta-tools cover discovery, inspection, and invocation, leaving no obvious gaps.