Cost and outcome metrics for one school: published tuition (in-state and out-of-state), average net price, six-year graduation rate, first-year retention, median earnings ten years after entry, admission rate, and SAT/ACT ranges.
| Name | Required | Description | Default |
|---|---|---|---|
| unit_id | Yes | IPEDS UNITID (Scorecard 'id'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value by disclosing the specific content scope: which cost and outcome metrics are included. It does not cover edge cases like missing data or data vintage, but for a read-only metrics tool with strong annotations this is adequate.
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?
One sentence that front-loads the resource type ('Cost and outcome metrics for one school') and then provides a compact, well-organized list of specific metrics. It is informative without redundancy or filler.
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 single-parameter read-only tool with no output schema, the description sufficiently conveys what data will be returned and the required input. It does not explain how to obtain the unit_id, but the schema's reference to IPEDS UNITID and the 'Scorecard id' is likely enough for an agent to relate it to college_search.
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% and the sole parameter unit_id is described as 'IPEDS UNITID (Scorecard id)', which fully documents what is needed. The description adds no additional parameter semantics, so the baseline score of 3 is appropriate.
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 type ('Cost and outcome metrics for one school') and enumerates the exact metrics returned. It does not use an imperative verb like 'get' or 'retrieve,' but the scope 'for one school' and the detailed metric list make the tool's purpose unambiguous and distinguish it from broader college_search or college_trends siblings.
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 phrase 'for one school' implies this tool is for a single-school lookup and contrasts implicitly with multi-school siblings like college_compare or college_search. However, it does not explicitly state when to prefer this over those alternatives or mention any prerequisites, such as needing a valid unit_id from search.
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 overlap heavily across domains: caselaw_search vs court_case_search vs court_opinion_search, caselaw_citation_lookup vs court_citation_resolver, and a cluster of company due-diligence tools (company_trust_check, counterparty_risk_score, entity_dossier, issuer_diligence_dossier, kyb_aml_evidence_case_file) that all screen a company for sanctions/risk/standing. With 290 tools, an agent will frequently face multiple equally plausible choices for the same user intent.
The vast majority of tools follow a clean domain-prefix + snake_case pattern (census_, eia_, fmcsa_, npi_, cfpb_, etc.), but there are notable exceptions: entity_resolve and resolve_entity are reversed duplicates, reg_search (Federal Register) sits next to reg_cfr_search (CFR) with confusingly similar names, and carrier_monitor_recheck deviates from the carrier_vetting_* family.
290 tools is an extreme count under any rubric, far exceeding even the 50+ threshold for the lowest score. While the group-filtering mechanism and meta-tools like list_tool_groups and search_available_datasets mitigate the practical burden, the raw surface is still massively oversized for an agent to select from accurately and efficiently.
For a read-only data-aggregation server, coverage is remarkably comprehensive across 59 domains, and generic fallbacks like cdc_dataset_query, eia_series_lookup, fred_observations, and bls_series prevent most dead ends. Minor gaps exist (a single GitHub tool, demo-only property_lookup coverage, no write/update operations anywhere), but the stated data-access purpose is well served.