Skip to main content
Glama

Asrs Search

asrs_search
Read-onlyIdempotent

Search NASA ASRS (Aviation Safety Reporting System) de-identified aviation safety incident reports by keyword, with optional filters. Answers "find reports about runway incursions", "ASRS reports mentioning bird strikes near a given airport", "fatigue reports involving commuter flight crews". Matches the query against each report's narrative, synopsis, topic and coded anomaly. Returns, per report, the ACN (Accession Number), date, airport/state, aircraft, flight phase, synopsis and a narrative excerpt — call asrs_report with the ACN for the full narrative. Covers NASA's thirty standing curated Report Sets (up to 50 reports each on a fixed safety topic, such as runway incursions, CFIT, bird strikes, NMACs, icing, fatigue), not NASA's full database — call asrs_topics to see which topics and date ranges are covered before concluding a topic has no reports.

Input Schema

NameRequiredDescriptionDefault
limitNoMax reports to return (default 50, max 200).
phaseNoFilter by flight phase substring, e.g. "taxi", "landing", "initial approach", "cruise".
queryNoKeyword(s) to search for in the report narrative, synopsis, topic and coded anomaly, e.g. "runway incursion", "bird strike", "fatigue". Multiple words require ALL of them to appear (not necessarily adjacent).
date_toNoOnly include reports up to this year-month, e.g. "2025-01".
aircraftNoFilter by aircraft/operator category substring, e.g. "widebody", "commercial fixed wing", "helicopter".
date_fromNoOnly include reports from this year-month or later, e.g. "2024-06" or "2024". Reports are dated by the month ASRS recorded them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds substantive context beyond that: the corpus is thirty curated Report Sets capped at ~50 reports each, and it documents the per-report return fields plus the ACN handoff to asrs_report. It doesn't mention ranking/relevance behavior for multi-word matching beyond what the schema says, keeping it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and example questions are front-loaded, and the handling of alternatives and coverage limits comes after. It is dense and mostly earns its length, though the triple quoted example queries are somewhat verbose relative to the information they convey.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six optional parameters, no output schema, and no enums, the description fills the remaining gaps: it states the return shape (ACN, date, airport/state, aircraft, phase, synopsis, excerpt), the corpus limitation, and the next-step tools. Nothing an agent needs to call this correctly or interpret results is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters (limit, query, phase, aircraft, date_from, date_to) are already documented with examples and semantics. The description restates which fields the query matches, which the schema already covers, so it adds little parameter-level meaning beyond the structured data — baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource (NASA ASRS de-identified incident reports) with scope qualifiers (keyword + optional filters). It explicitly distinguishes itself from siblings by naming asrs_report (full narrative) and asrs_topics (topic coverage), so an agent can route correctly without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage contexts via quoted example questions, names the two alternatives and the conditions that select them (asrs_report with an ACN for the full narrative; asrs_topics to see covered topics/date ranges). It also sets an explicit negative boundary: this is not NASA's full database, and advises checking topics before concluding no reports exist.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.