canon_changesAggregated dated change events across every vertical, newest first. Poll this instead of re-crawling.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ISO date; only events on or after this date |
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?
Annotations already mark the tool read-only and open-world, and the description adds useful behavioral details: results are aggregated, dated, span every vertical, and are returned newest first. This gives an agent a solid expectation of the response without contradicting the annotations.
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 with no filler: the first delivers the core behavior and ordering, and the second gives actionable usage guidance. Every word earns its place, and the description is appropriately sized for a simple single-parameter tool.
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 simple polling tool with one optional parameter, read-only and open-world annotations, and a fully documented schema, the description provides enough context to select and call the tool correctly. It does not detail the shape of individual change events or pagination, but those are minor gaps given the strong annotations and schema.
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 100%, with the 'since' parameter fully documented as an ISO date filtering to events on or after that date. The description does not add extra parameter nuance, but it does not need to because the schema already covers semantics.
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 identifies the resource: aggregated dated change events across every vertical, ordered newest first. It stops short of an explicit verb like 'list' or 'retrieve', but the intent is unambiguous and the tool is distinct from its sibling tools.
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?
'Poll this instead of re-crawling' gives direct guidance on when to use the tool as a change-polling mechanism rather than performing heavier data collection. It does not name specific alternatives or exclusion cases, but the primary usage context is clear.
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 clearly distinct job: searching, fetching entries, mapping entities, running formulas, batching computations, verifying receipts, citing, listing sites, monitoring changes, and looking up regulatory thresholds. Even the related compute/batch/verify tools are cleanly separated by single vs. batch execution and verification responsibility.
All tools share the canon_ prefix and use lowercase snake_case, which makes the set feel consistent and predictable. However, the suffixes mix bare resource nouns (canon_sites, canon_thresholds, canon_entity) with verb phrases (canon_describe_formula, canon_list_formulas, canon_get_entry), so the naming convention is not perfectly uniform.
Thirteen tools is well within the ideal range for a reference-and-computation API, and each tool covers a distinct capability without redundancy. The count feels proportionate to the breadth of the finance canon domain.
The surface is complete for a read-only reference service: search, entry retrieval, entity resolution, contract lookup, formula inspection, computation, batch execution, receipt verification, citations, change monitoring, site stats, and regulatory thresholds. There are no obvious dead ends or missing core operations.