Public procurement (SEAP) awards for one company: contracts it won, and contracts it granted as a contracting authority. Bounded to the 200 most recent per side; total reports the true count, which can be far larger.
| Name | Required | Description | Default |
|---|---|---|---|
| cui | Yes | ||
| role | No | both |
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?
Since no annotations are provided, the description carries the full burden of behavioral disclosure. It usefully reveals that results are bounded to the 200 most recent per side and that the `total` field reflects the true count, which may be much larger—important expectations for callers. It does not mention authentication, errors, or rate limits, but the limit/count disclosure is genuinely informative.
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 with no filler; the first sentence states what the tool returns, and the second covers a critical sampling-bound behavior. Every clause contributes useful information, and the most important scoping detail is front-loaded.
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 tool with no output schema and sparse parameter documentation, the description gives a solid overview but omits specifics about the `role` parameter values and the `cui` identifier. The limit and total behavior are well covered, but an agent still has to infer how to request 'won side' versus 'granted side' through the parameters.
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?
With 0% schema description coverage, the description must compensate for the `cui` and `role` parameters. It clarifies that the tool operates on one company and hints at two sides (won vs. granted), which maps loosely to `role`, but it never explicitly defines valid role values or states how `cui` should be formatted. The compensation is partial rather than complete.
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 (SEAP public procurement awards) and the specific subject (one company), covering both directions: contracts won and contracts granted. It is distinct from sibling tools focused on financials, officers, or company metadata, so an agent can tell it apart.
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 this tool is for retrieving procurement awards for a single company, but it does not explicitly state when to choose it over siblings like get_company or company_stats, nor does it provide when-not-to-use guidance. The context is sufficient for a straightforward selection, but alternatives and exclusions are left unstated.
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.
Most tools have clearly distinct domains: company identity, financials, legal, officers, procurement, stats, and CAEN lookup. The only ambiguity comes from the redundant connector aliases (fetch vs get_company, search vs search_companies), but their descriptions explicitly call out the duplication and direct agents to the canonical tools.
The set mostly follows a clear verb_noun convention: get_company, get_financials, get_officers, list_companies, search_companies, resolve_caen. Minor deviations are company_stats (noun_verb) and the bare connector aliases fetch and search, but all names are lowercase and underscore-separated, so the pattern remains predictable.
With 12 tools, the surface is well-scoped for a company information/registry API. Each tool covers a meaningful slice of the domain—search, company details, financials, legal, officers, procurement, stats, metadata, and CAEN resolution—without redundant or trivial additions beyond the two explicitly labeled connector aliases.
For a read-only company data API, the coverage is thorough: name/CUI resolution, company identity with optional includes, full financial history, legal records, officers, procurement, and aggregate statistics are all present. There are no obvious dead ends; even data freshness and completeness are addressed by get_meta.