Multi-year trend for one school sourced from the Urban Institute Education Data Portal (IPEDS). Choose a metric (enrollment, graduation_rate, retention, cost) and a year range.
| Name | Required | Description | Default |
|---|---|---|---|
| metric | Yes | Trend metric. | |
| unit_id | Yes | IPEDS UNITID. | |
| end_year | Yes | Last academic year, e.g. 2022. | |
| start_year | Yes | First academic year, e.g. 2010. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate safety. It adds the data source and per-school scoping, but it does not describe any quirks such as data availability, result shape, or behavior when no trend data exists.
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 carry the core purpose, scope, source, metric choices, and time dimension with no filler. The key differentiator ('one school') 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 simple read-only trend tool, the description provides enough context: single-school scope, supported metrics, year range, and data provenance. It lacks an explicit description of the output format, but no output schema exists and the meaning of 'trend' makes the expected return reasonably clear.
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?
Input schema already covers all four parameters at 100%, including descriptions and an enum for metric. The description adds nothing beyond echoing the metric choices and the idea of a year range, so the baseline 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 identifies a specific deliverable (multi-year trend), a scope (one school), and supported metrics plus a year range. It is distinguishable from sibling college tools like college_compare by the explicit 'one school' scope, though it uses a noun phrase rather than an action verb.
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 'one school' and 'multi-year trend' language tells an agent when this tool is appropriate, and the metric/year-range instruction indicates how to shape the request. It does not explicitly name alternative college tools or state when not to use this tool, so it stops short of full routing guidance.
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.