Drillable
Server Details
A multi-domain reference corpus where every answer drills down to its cited, verified source.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.4/5 across 7 of 7 tools scored.
Each tool has a clearly distinct purpose: lookup for definitions, search for queries, enumerate for complete sets, compute for aggregates, verify for claim checking, describe for discovery, and call for invocation. There is no ambiguity or overlap; the descriptions explicitly guide when to use each tool.
All tool names are single lowercase verbs: call, compute, describe, enumerate, lookup, search, verify. They follow a consistent pattern and are immediately intuitive for their functions.
With 7 tools, the server is well-scoped for a knowledge base that provides lookup, search, enumeration, computation, verification, discovery, and invocation. Each tool earns its place, covering the full interaction spectrum without being bloated.
The tool surface covers all essential operations: lookup definitions, search records, enumerate complete sets, compute aggregates, verify claims, discover capabilities, and invoke domain-specific verbs. A minor gap is the lack of a tool to list all domains directly without using describe, but this is a very minor oversight in an otherwise comprehensive set.
Available Tools
7 toolscallCall a domain verbARead-onlyInspect
Invoke a domain verb discovered via describe: call(domain, tool, args). Identical to the namespaced tool surface — every answer drills to its source; a miss is a typed abstention (logged as demand), never a guess. Do NOT invent tool names — take them from describe.
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | Arguments for that verb, per its describe() inputSchema. | |
| tool | Yes | The domain verb to invoke (e.g. 'reachable_cocktails'). | |
| domain | Yes | The mounted domain (e.g. 'cocktail'). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context: every miss is a typed abstention logged as demand, and never a guess. However, the readOnlyHint annotation already indicates it's safe; the description does not contradict but adds only minor detail about logging, not covering potential side effects from invoked verbs.
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 concise (two sentences) and front-loaded with the core purpose. It efficiently conveys the key constraints and behavior without fluff, though slightly dense.
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 meta-tool that delegates to dynamic verbs, the description adequately covers the pattern, relationship with `describe`, miss behavior, and naming constraint. No output schema is needed as return depends on invoked verb. It is sufficiently complete given the tool's nature.
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 coverage is 100%, and the description adds value by explaining that `args` follows the schema from `describe()`. This connects the parameters to the broader discovery workflow, beyond what the schema's property descriptions provide.
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 states the tool invokes a domain verb discovered via `describe`, explaining its role as a dynamic invocation mechanism. It distinguishes itself by emphasizing that it's identical to the namespaced tool surface and explicitly warns against inventing names.
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 provides clear guidance: do not invent tool names, only use verbs from `describe`. It implicitly distinguishes from sibling `describe` (discovery vs. invocation). However, it lacks explicit when-to-use or when-not-to-use comparisons with other siblings like `lookup` or `search`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
computeCount or group a domain's recordsARead-onlyInspect
A deterministic AGGREGATE over ONE corpus's COMPLETE set — the calculated-query shape ("how many X", "break X down by Y", "which is most common"). Requires domain; optional filter scopes the set (e.g. {"spirit":"gin"}); optional by (a record field) returns the count PER value, sorted, with the largest. Built ON enumerate, so it inherits the completeness contract: over an INCOMPLETE set it ABSTAINS rather than undercount. It counts on GROUND and refuses to crown a "best"/worth ranking (that has no oracle — the user's call). For the records/categories themselves use enumerate. Mounted corpora: acupuncture, cocktail, camera, law, copyright, trademark, music-theory, supplements, writing-style, minecraft-dungeons, spanish, medical-denials, languages, behavioral-econ, baseball, agent-practices, pokemon, mcp, readability, citations, relay, models, self-oracle, recall-traps, units, tax, physics, logic, astronomy, biology, geography, medicine, chemistry, calendar, math, eurorack, building-codes, cooking, personal-finance, stardew, coffee, electronics, physiology, diving, decibels, gearing, colorimetry, subnetting, textile-gauge, first-aid, statistics, chess-endgames, woodworking, rating-systems, tuning, check-digits, paper-sizes, wire-gauge, preferred-numbers, swe-claim-denial, psychology, roman-numerals, minecraft-mods, encodings, strength-training, hardiness-zones, terraria, unix-permissions, aspect-ratio, number-bases, resistor-color-code, cognitive-psychology, braille, semver, cron, unicode, timezones, metar, incoterms, soundex, glob, ieee754, http-status, zigbee, uuid, base-encodings, percent-encoding, dms-coordinates, gray-code, hashing, classical-ciphers, hamming-code, geohash, mac-address, poker-hands, capacitor-codes, iso-duration, dice-probability, scrabble-score, wind-chill, mach-number, saffir-simpson, dataviz, patents, chords, dtmf, shoe-size, crc, base58, bech32, base85, reed-solomon, theoretical-ecology, string-similarity, checksums, compression, prng, bloom-filter, computus, hyperloglog, peppers, search-heuristics, tomatoes, solar-times, blood-alcohol, maidenhead-locator, brewing, celestial-navigation, electrochemistry, fluid-mechanics, information-theory, structural-mechanics, regex, combinatorics, graph-algorithms, linear-algebra, psychrometrics, photographic-exposure, photometry, rf-link, screen-resolution, algorithm-complexity, color-names, type-sizes, vin, drill-bit-sizing, iso-country-codes, itu-e164, mime-types, coding-theory, finite-automata, fourier-analysis, numerical-methods, ac-circuits, heat-transfer, markov-chains, orbital-mechanics, currency-codes, elliptic-curves, queueing-theory, totp-hotp, computational-geometry, crockford-base32, html-named-character-references, iana-port-numbers, thermodynamics, acoustics, magnetism, hydrostatics, gas-laws, blackbody-radiation, antenna-gain, bcp47, dimensionless-numbers, iso-language-codes, dns-record-types, midi-messages, kinematics, geometric-optics, digital-logic, convex-optimization, clothing-sizes, knitting-needle-gauge, pipe-size, winemaking-math, ansi-escape-codes, radiation-dosimetry, transmission-lines, nuclear-decay, cribbage-scoring, running-pace, dnd-math, bowling-scoring, tire-size, abn-acn, sedol-cusip, damm-verhoeff, iso-6346, iso-7064, fresnel-equations, hydrogen-spectrum, material-elasticity, pump-affinity, control-theory, em-plane-waves, ordinary-differential-equations, iso-639-reference, posix-signals-reference, quaternions-reference, bayesian-inference, issn-check, ean-barcode, iana-uri-schemes, aquarium-chemistry, 3d-printing, iso-thread, arrow-spine, knitting-needle-sizes, bearing-sizes, camera-film-formats, horology, mechanical-vibrations, rocket-propulsion, fiber-optics, rolling-element-bearing-life, beaufort-scale, iec-60320, iana-protocol-numbers, sae-viscosity, hat-sizes, darts-scoring, complex-numbers, boolean-algebra, game-theory, lambda-calculus, combustion-stoichiometry, bolts-screws, ham-radio-bands, miniature-scale, fracture-mechanics, torsion, catenary, standard-atmosphere, open-channel-hydraulics, gaussian-beam-optics, capillary-action, nato-phonetic, lei, fen-pgn, nmea-0183, phonetic-algorithms, lumber-grades-dimensions, film-speed-iso, telescope-optics, tabletop-rpg-probability, tcr-therapy, software-licenses, z-transform, generating-functions, terzaghi-bearing-capacity, icao-doc8643, imei-reference, gs1-ai, ulid, postal-barcodes, photographic-paper-sizes, gauge-systems-industrial, fishing-line-ratings, sorting-algorithms, candle-making, pool-billiards-geometry, sourdough-ratios, electromagnetic-induction, ring-sizes, probability-distributions, isentropic-flow, fatigue-life, three-phase-power, http-headers, ghs-hazard, abrasive-grit-sizes, cycling-power-zones, group-theory, dynamic-programming-recurrences, molecular-diffusion, smtp-reply-codes, un-locode, chain-pitch, string-gauges, sewing-pattern-grading, tabletop-wargaming-probability, aquaculture-stocking-density, polynomial-arithmetic, matrix-decompositions, nhs-number, diode-junction, elastic-collisions, pressure-vessel, reverberation-time, count-min-sketch, ieee-ethertypes, icao-mrz, http-methods, tls-alerts, bwt-mtf, bicycle-wheel-sizing, silk-thread-nm-denier, soapmaking-lye, iso-3166-2, context-free-grammars, dc-motor-equations, usb-class-codes, punycode, film-frame-rates, aperture-f-stop-series, golf-handicap, hydroponics-nutrients, sewing-fabric-math, resin-mixing-ratios, pdf-structure, piping-water-hammer, hertzian-contact-stress, photovoltaic-cell-performance, un-ece-vegetable-fruit-grading-standards, iata-airport-delay-codes, un-transport-hazard-class-un-numbers, faa-nas-airspace-classes, sieve-mesh-sizing, disc-golf-flight-numbers, beekeeping-hive-math, vinyl-record-cutting-specs, houseplant-light-and-watering-calc, cellular-automata-rules, error-correcting-codes-beyond-block, climbing-rope-and-anchor-ratings, knot-invariants, photovoltaic-cell-model, fiber-dispersion, osmotic-pressure-solutions, faa-n-number, naics-sic-classification, orcid-checksum, swift-bic-format, isni-checksum, shotgun-gauge-and-choke, rope-cordage-strength-and-diameter, screen-mesh-count-and-particle-sizing, battery-cell-form-factor-codes, xor-filter, kite-line-and-wind-window, clothing-glove-size-standards, wasm-module-header, protobuf-wire-format, rankine-cycle-efficiency, projectile-ballistics-drag-corrected, faa-airport-codes, aes-fips-block-parameters, voronoi-delaunay, iso15459-license-plate, np-completeness-reductions, hidden-markov-viterbi, png-ihdr-fields, mbr-partition-table, fuzzywuzzy-rapidfuzz-string-similarity-api-reference, v-belt-sprocket-sizing, e164-carrier-mnc-mcc, faa-nav-aid-frequency-bands, go-baduk-scoring, zip-central-directory-header, curling-scoring, mahjong-hand-scoring, sudoku-difficulty-rating, dominoes-scoring, base45, typography, tides, pbkdf2, ndc, epsg, hkdf, hvac-duct-sizing, hts, elevator-rope-crane-wire-rope-classification, board-game-elo-scoring, ecfr, tide-and-moon-phase-almanac, regular-expression-derivatives, obd2-pids, emission-designators, runway-designators, qr-code, iban-structure, sewing-needle, experiment-design, iana-link-relations, scientific-method, mtg-rules, crystallography.
| Name | Required | Description | Default |
|---|---|---|---|
| by | No | Optional: a record field to group the count by (e.g. 'family'). Omit for a plain count. Discover fields via `enumerate`. | |
| domain | Yes | The corpus to compute over (required). | |
| filter | No | Optional faceted constraints to scope the set (e.g. {"spirit":"gin"}). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond the 'readOnlyHint' annotation: it is deterministic, aggregates over complete sets, inherits a completeness contract from 'enumerate', abstains if the set is incomplete, and refuses to rank or crown a best. This informs the agent about important constraints and edge cases.
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 extremely verbose, including a long list of mounted corpora that could be condensed or referenced elsewhere. While the core explanation is front-loaded, the excessive length detracts from clarity and efficient parsing. Every sentence does not earn its place.
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?
Given the tool's complexity and lack of output schema, the description covers the aggregate behavior, completeness contract, and parameter usage adequately. However, it does not describe the return format or value interpretation. For a tool that returns counts and groupings, this is a gap, though the context is otherwise fairly complete.
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?
Since schema description coverage is 100%, the baseline is 3. The description adds value with examples (e.g., filter with '{"spirit":"gin"}') and guidance for the 'by' parameter (e.g., 'Discover fields via enumerate'). This helps the agent understand parameter usage beyond the schema.
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 states the tool's purpose: 'Count or group a domain's records' and elaborates on the calculated-query shape. It distinguishes from sibling 'enumerate' by explicitly stating that for the records/categories themselves, use 'enumerate'. The verb 'compute' combined with the title and description provides a specific resource and action.
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 provides explicit guidance on when to use this tool versus 'enumerate' (for records/categories themselves). It also explains the optional parameters 'filter' and 'by' and their roles. However, it does not address other siblings like 'call', 'lookup', or 'search', leaving potential ambiguity for those alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
describeDescribe a domain's toolsARead-onlyInspect
Discover the fleet's deeper machinery. No args → every mounted domain with its verbs grouped by rung (lookup → composability → contested → frontier). With domain → that domain's full tool list with descriptions and input schemas. Invoke anything it lists via call. Use this whenever the spine (lookup/search/verify) is too shallow for the question — e.g. "what can I make/patch/cover with MY inventory", contested claims, open questions.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | Optional: one domain's full tool schemas (e.g. 'cocktail'). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description aligns by using verbs like 'discover' and 'list'. No contradiction. The description adds behavioral context about returning grouped verb lists and the ability to invoke listed tools via 'call'. This goes beyond the annotation's simple read-only flag.
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 concise (three sentences) yet packed with all necessary information: purpose, behavior for both input cases, usage guidance, and connection to sibling tool 'call'. No wasted words; front-loaded with the main action.
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?
Given the tool's complexity (tool introspection), single optional parameter, no output schema, and presence of annotations, the description covers all necessary aspects: both invocation modes, when to use, and how it relates to other tools. No gaps identified.
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 coverage is 100% for the single optional parameter 'domain' with a basic description. The description adds significant meaning: explaining the two modes (no arg vs. domain) and what each returns. This clarifies the parameter's semantics beyond the schema alone. Baseline 3, plus 1 for added value.
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 states the tool's purpose: discovering domains and their tools. It specifies behavior for no arguments (list all domains grouped by rung) and with a domain (full tool list with schemas). It distinguishes itself from siblings by referencing deeper discovery beyond lookup/search/verify.
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?
Explicit usage guidance is given: 'Use this whenever the spine (lookup/search/verify) is too shallow for the question.' Concrete examples follow: 'what can I make/patch/cover with MY inventory', contested claims, open questions. This clearly tells the agent when to invoke this tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
enumerateList a domain's categories or complete setARead-onlyInspect
List broad CATEGORIES or the COMPLETE set within ONE corpus — the shape search cannot serve (search returns a ranked, capped sample, not the whole set). Requires domain. Returns every category axis with exact counts, and — with an optional filter (faceted constraints, e.g. {"spirit":"gin"}) — the COMPLETE record set scoped by it, marked complete. A count/aggregate is sound ONLY over a complete set; an incomplete return is flagged, never silently undercounted (the completeness contract). Use for "what kinds are there", "all the X", "how many X"; for one record use lookup/search. Discover a domain's facets via describe. The special domain directory enumerates the FLEET itself — the algorithm domains drillable holds (declared registry tags, faceted by class/grain; e.g. "what algorithms are there?"). Mounted corpora: acupuncture, cocktail, camera, law, copyright, trademark, music-theory, supplements, writing-style, minecraft-dungeons, spanish, medical-denials, languages, behavioral-econ, baseball, agent-practices, pokemon, mcp, readability, citations, relay, models, self-oracle, recall-traps, units, tax, physics, logic, astronomy, biology, geography, medicine, chemistry, calendar, math, eurorack, building-codes, cooking, personal-finance, stardew, coffee, electronics, physiology, diving, decibels, gearing, colorimetry, subnetting, textile-gauge, first-aid, statistics, chess-endgames, woodworking, rating-systems, tuning, check-digits, paper-sizes, wire-gauge, preferred-numbers, swe-claim-denial, psychology, roman-numerals, minecraft-mods, encodings, strength-training, hardiness-zones, terraria, unix-permissions, aspect-ratio, number-bases, resistor-color-code, cognitive-psychology, braille, semver, cron, unicode, timezones, metar, incoterms, soundex, glob, ieee754, http-status, zigbee, uuid, base-encodings, percent-encoding, dms-coordinates, gray-code, hashing, classical-ciphers, hamming-code, geohash, mac-address, poker-hands, capacitor-codes, iso-duration, dice-probability, scrabble-score, wind-chill, mach-number, saffir-simpson, dataviz, patents, chords, dtmf, shoe-size, crc, base58, bech32, base85, reed-solomon, theoretical-ecology, string-similarity, checksums, compression, prng, bloom-filter, computus, hyperloglog, peppers, search-heuristics, tomatoes, solar-times, blood-alcohol, maidenhead-locator, brewing, celestial-navigation, electrochemistry, fluid-mechanics, information-theory, structural-mechanics, regex, combinatorics, graph-algorithms, linear-algebra, psychrometrics, photographic-exposure, photometry, rf-link, screen-resolution, algorithm-complexity, color-names, type-sizes, vin, drill-bit-sizing, iso-country-codes, itu-e164, mime-types, coding-theory, finite-automata, fourier-analysis, numerical-methods, ac-circuits, heat-transfer, markov-chains, orbital-mechanics, currency-codes, elliptic-curves, queueing-theory, totp-hotp, computational-geometry, crockford-base32, html-named-character-references, iana-port-numbers, thermodynamics, acoustics, magnetism, hydrostatics, gas-laws, blackbody-radiation, antenna-gain, bcp47, dimensionless-numbers, iso-language-codes, dns-record-types, midi-messages, kinematics, geometric-optics, digital-logic, convex-optimization, clothing-sizes, knitting-needle-gauge, pipe-size, winemaking-math, ansi-escape-codes, radiation-dosimetry, transmission-lines, nuclear-decay, cribbage-scoring, running-pace, dnd-math, bowling-scoring, tire-size, abn-acn, sedol-cusip, damm-verhoeff, iso-6346, iso-7064, fresnel-equations, hydrogen-spectrum, material-elasticity, pump-affinity, control-theory, em-plane-waves, ordinary-differential-equations, iso-639-reference, posix-signals-reference, quaternions-reference, bayesian-inference, issn-check, ean-barcode, iana-uri-schemes, aquarium-chemistry, 3d-printing, iso-thread, arrow-spine, knitting-needle-sizes, bearing-sizes, camera-film-formats, horology, mechanical-vibrations, rocket-propulsion, fiber-optics, rolling-element-bearing-life, beaufort-scale, iec-60320, iana-protocol-numbers, sae-viscosity, hat-sizes, darts-scoring, complex-numbers, boolean-algebra, game-theory, lambda-calculus, combustion-stoichiometry, bolts-screws, ham-radio-bands, miniature-scale, fracture-mechanics, torsion, catenary, standard-atmosphere, open-channel-hydraulics, gaussian-beam-optics, capillary-action, nato-phonetic, lei, fen-pgn, nmea-0183, phonetic-algorithms, lumber-grades-dimensions, film-speed-iso, telescope-optics, tabletop-rpg-probability, tcr-therapy, software-licenses, z-transform, generating-functions, terzaghi-bearing-capacity, icao-doc8643, imei-reference, gs1-ai, ulid, postal-barcodes, photographic-paper-sizes, gauge-systems-industrial, fishing-line-ratings, sorting-algorithms, candle-making, pool-billiards-geometry, sourdough-ratios, electromagnetic-induction, ring-sizes, probability-distributions, isentropic-flow, fatigue-life, three-phase-power, http-headers, ghs-hazard, abrasive-grit-sizes, cycling-power-zones, group-theory, dynamic-programming-recurrences, molecular-diffusion, smtp-reply-codes, un-locode, chain-pitch, string-gauges, sewing-pattern-grading, tabletop-wargaming-probability, aquaculture-stocking-density, polynomial-arithmetic, matrix-decompositions, nhs-number, diode-junction, elastic-collisions, pressure-vessel, reverberation-time, count-min-sketch, ieee-ethertypes, icao-mrz, http-methods, tls-alerts, bwt-mtf, bicycle-wheel-sizing, silk-thread-nm-denier, soapmaking-lye, iso-3166-2, context-free-grammars, dc-motor-equations, usb-class-codes, punycode, film-frame-rates, aperture-f-stop-series, golf-handicap, hydroponics-nutrients, sewing-fabric-math, resin-mixing-ratios, pdf-structure, piping-water-hammer, hertzian-contact-stress, photovoltaic-cell-performance, un-ece-vegetable-fruit-grading-standards, iata-airport-delay-codes, un-transport-hazard-class-un-numbers, faa-nas-airspace-classes, sieve-mesh-sizing, disc-golf-flight-numbers, beekeeping-hive-math, vinyl-record-cutting-specs, houseplant-light-and-watering-calc, cellular-automata-rules, error-correcting-codes-beyond-block, climbing-rope-and-anchor-ratings, knot-invariants, photovoltaic-cell-model, fiber-dispersion, osmotic-pressure-solutions, faa-n-number, naics-sic-classification, orcid-checksum, swift-bic-format, isni-checksum, shotgun-gauge-and-choke, rope-cordage-strength-and-diameter, screen-mesh-count-and-particle-sizing, battery-cell-form-factor-codes, xor-filter, kite-line-and-wind-window, clothing-glove-size-standards, wasm-module-header, protobuf-wire-format, rankine-cycle-efficiency, projectile-ballistics-drag-corrected, faa-airport-codes, aes-fips-block-parameters, voronoi-delaunay, iso15459-license-plate, np-completeness-reductions, hidden-markov-viterbi, png-ihdr-fields, mbr-partition-table, fuzzywuzzy-rapidfuzz-string-similarity-api-reference, v-belt-sprocket-sizing, e164-carrier-mnc-mcc, faa-nav-aid-frequency-bands, go-baduk-scoring, zip-central-directory-header, curling-scoring, mahjong-hand-scoring, sudoku-difficulty-rating, dominoes-scoring, base45, typography, tides, pbkdf2, ndc, epsg, hkdf, hvac-duct-sizing, hts, elevator-rope-crane-wire-rope-classification, board-game-elo-scoring, ecfr, tide-and-moon-phase-almanac, regular-expression-derivatives, obd2-pids, emission-designators, runway-designators, qr-code, iban-structure, sewing-needle, experiment-design, iana-link-relations, scientific-method, mtg-rules, crystallography.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The corpus to enumerate (required), e.g. 'cocktail'. | |
| filter | No | Optional faceted constraints to scope the complete set (e.g. {"family":"sour"}). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true. Description adds behavioral details: returns are marked 'complete' if full, incomplete returns flagged, and counts only sound over complete sets. No contradictions.
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 long due to a list of mounted corpora, which adds verbosity. However, it is structured and front-loaded with core purpose, so it is decent but not maximally concise.
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?
No output schema, but description explains return shape: categories with counts or complete record sets, and special domain 'directory'. Covers use cases adequately.
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 coverage is 100%, baseline 3. Description adds context for 'domain' (required) and 'filter' (optional faceted constraints) with an example, beyond the schema.
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 states the tool lists categories or complete sets within a corpus, using specific verbs and distinguishing from siblings like 'search', 'lookup', and 'describe'.
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?
Explicitly states when to use: for 'what kinds are there', 'all the X', 'how many X'; and when not to use: for one record use 'lookup' or 'search'. Also explains limitations of 'search'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
lookupLook up a conceptARead-onlyInspect
Define a concept/term from a domain's glossary (e.g. 'stir', 'crop-factor', 'roughness'). Routes to each domain's lookup_concept; pass domain to target one, omit to fan out. For entities/records use search. Abstains on a miss, which is logged as a gap (the demand signal) — there is no report_gap verb. For COMPUTED quantities (molar mass, date math, unit conversions) a miss will point you to the right compute verb — follow it via describe/call rather than re-searching. Mounted corpora: acupuncture, cocktail, camera, law, copyright, trademark, music-theory, supplements, writing-style, minecraft-dungeons, spanish, medical-denials, languages, behavioral-econ, baseball, agent-practices, pokemon, mcp, readability, citations, relay, models, self-oracle, recall-traps, units, tax, physics, logic, astronomy, biology, geography, medicine, chemistry, calendar, math, eurorack, building-codes, cooking, personal-finance, stardew, coffee, electronics, physiology, diving, decibels, gearing, colorimetry, subnetting, textile-gauge, first-aid, statistics, chess-endgames, woodworking, rating-systems, tuning, check-digits, paper-sizes, wire-gauge, preferred-numbers, swe-claim-denial, psychology, roman-numerals, minecraft-mods, encodings, strength-training, hardiness-zones, terraria, unix-permissions, aspect-ratio, number-bases, resistor-color-code, cognitive-psychology, braille, semver, cron, unicode, timezones, metar, incoterms, soundex, glob, ieee754, http-status, zigbee, uuid, base-encodings, percent-encoding, dms-coordinates, gray-code, hashing, classical-ciphers, hamming-code, geohash, mac-address, poker-hands, capacitor-codes, iso-duration, dice-probability, scrabble-score, wind-chill, mach-number, saffir-simpson, dataviz, patents, chords, dtmf, shoe-size, crc, base58, bech32, base85, reed-solomon, theoretical-ecology, string-similarity, checksums, compression, prng, bloom-filter, computus, hyperloglog, peppers, search-heuristics, tomatoes, solar-times, blood-alcohol, maidenhead-locator, brewing, celestial-navigation, electrochemistry, fluid-mechanics, information-theory, structural-mechanics, regex, combinatorics, graph-algorithms, linear-algebra, psychrometrics, photographic-exposure, photometry, rf-link, screen-resolution, algorithm-complexity, color-names, type-sizes, vin, drill-bit-sizing, iso-country-codes, itu-e164, mime-types, coding-theory, finite-automata, fourier-analysis, numerical-methods, ac-circuits, heat-transfer, markov-chains, orbital-mechanics, currency-codes, elliptic-curves, queueing-theory, totp-hotp, computational-geometry, crockford-base32, html-named-character-references, iana-port-numbers, thermodynamics, acoustics, magnetism, hydrostatics, gas-laws, blackbody-radiation, antenna-gain, bcp47, dimensionless-numbers, iso-language-codes, dns-record-types, midi-messages, kinematics, geometric-optics, digital-logic, convex-optimization, clothing-sizes, knitting-needle-gauge, pipe-size, winemaking-math, ansi-escape-codes, radiation-dosimetry, transmission-lines, nuclear-decay, cribbage-scoring, running-pace, dnd-math, bowling-scoring, tire-size, abn-acn, sedol-cusip, damm-verhoeff, iso-6346, iso-7064, fresnel-equations, hydrogen-spectrum, material-elasticity, pump-affinity, control-theory, em-plane-waves, ordinary-differential-equations, iso-639-reference, posix-signals-reference, quaternions-reference, bayesian-inference, issn-check, ean-barcode, iana-uri-schemes, aquarium-chemistry, 3d-printing, iso-thread, arrow-spine, knitting-needle-sizes, bearing-sizes, camera-film-formats, horology, mechanical-vibrations, rocket-propulsion, fiber-optics, rolling-element-bearing-life, beaufort-scale, iec-60320, iana-protocol-numbers, sae-viscosity, hat-sizes, darts-scoring, complex-numbers, boolean-algebra, game-theory, lambda-calculus, combustion-stoichiometry, bolts-screws, ham-radio-bands, miniature-scale, fracture-mechanics, torsion, catenary, standard-atmosphere, open-channel-hydraulics, gaussian-beam-optics, capillary-action, nato-phonetic, lei, fen-pgn, nmea-0183, phonetic-algorithms, lumber-grades-dimensions, film-speed-iso, telescope-optics, tabletop-rpg-probability, tcr-therapy, software-licenses, z-transform, generating-functions, terzaghi-bearing-capacity, icao-doc8643, imei-reference, gs1-ai, ulid, postal-barcodes, photographic-paper-sizes, gauge-systems-industrial, fishing-line-ratings, sorting-algorithms, candle-making, pool-billiards-geometry, sourdough-ratios, electromagnetic-induction, ring-sizes, probability-distributions, isentropic-flow, fatigue-life, three-phase-power, http-headers, ghs-hazard, abrasive-grit-sizes, cycling-power-zones, group-theory, dynamic-programming-recurrences, molecular-diffusion, smtp-reply-codes, un-locode, chain-pitch, string-gauges, sewing-pattern-grading, tabletop-wargaming-probability, aquaculture-stocking-density, polynomial-arithmetic, matrix-decompositions, nhs-number, diode-junction, elastic-collisions, pressure-vessel, reverberation-time, count-min-sketch, ieee-ethertypes, icao-mrz, http-methods, tls-alerts, bwt-mtf, bicycle-wheel-sizing, silk-thread-nm-denier, soapmaking-lye, iso-3166-2, context-free-grammars, dc-motor-equations, usb-class-codes, punycode, film-frame-rates, aperture-f-stop-series, golf-handicap, hydroponics-nutrients, sewing-fabric-math, resin-mixing-ratios, pdf-structure, piping-water-hammer, hertzian-contact-stress, photovoltaic-cell-performance, un-ece-vegetable-fruit-grading-standards, iata-airport-delay-codes, un-transport-hazard-class-un-numbers, faa-nas-airspace-classes, sieve-mesh-sizing, disc-golf-flight-numbers, beekeeping-hive-math, vinyl-record-cutting-specs, houseplant-light-and-watering-calc, cellular-automata-rules, error-correcting-codes-beyond-block, climbing-rope-and-anchor-ratings, knot-invariants, photovoltaic-cell-model, fiber-dispersion, osmotic-pressure-solutions, faa-n-number, naics-sic-classification, orcid-checksum, swift-bic-format, isni-checksum, shotgun-gauge-and-choke, rope-cordage-strength-and-diameter, screen-mesh-count-and-particle-sizing, battery-cell-form-factor-codes, xor-filter, kite-line-and-wind-window, clothing-glove-size-standards, wasm-module-header, protobuf-wire-format, rankine-cycle-efficiency, projectile-ballistics-drag-corrected, faa-airport-codes, aes-fips-block-parameters, voronoi-delaunay, iso15459-license-plate, np-completeness-reductions, hidden-markov-viterbi, png-ihdr-fields, mbr-partition-table, fuzzywuzzy-rapidfuzz-string-similarity-api-reference, v-belt-sprocket-sizing, e164-carrier-mnc-mcc, faa-nav-aid-frequency-bands, go-baduk-scoring, zip-central-directory-header, curling-scoring, mahjong-hand-scoring, sudoku-difficulty-rating, dominoes-scoring, base45, typography, tides, pbkdf2, ndc, epsg, hkdf, hvac-duct-sizing, hts, elevator-rope-crane-wire-rope-classification, board-game-elo-scoring, ecfr, tide-and-moon-phase-almanac, regular-expression-derivatives, obd2-pids, emission-designators, runway-designators, qr-code, iban-structure, sewing-needle, experiment-design, iana-link-relations, scientific-method, mtg-rules, crystallography.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The concept/entity to resolve. | |
| domain | No | Optional: restrict to one domain (e.g. 'acupuncture'). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, indicating safe read-only behavior. The description adds that the tool 'abstains on a miss, which is logged as a gap' and that there is no report_gap verb, providing extra behavioral context without contradicting 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?
The description is well-structured with a clear purpose statement, usage guidance, and a list of mounted corpora. While the domain list is long, it provides useful scope information for the agent. Every part serves a purpose, though it could be slightly more concise.
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?
Despite no output schema, the description covers input semantics, routing logic, miss behavior, and domain scope. For a lookup tool with many potential domains, it provides sufficient context for correct invocation, though the output format is not described.
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 coverage is 100%, giving a baseline of 3. The description adds semantic value by explaining that 'query' is the concept/term to resolve, 'domain' is optional to restrict or omit for all, and lists many example domains. This context enriches understanding beyond the schema.
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 states that the tool defines a concept/term from a domain's glossary, with examples like 'stir' and 'crop-factor'. It distinguishes itself from sibling tools by specifying that 'search' is for entities/records and that computes are handled by other verbs. The verb 'lookup' with resource 'concept' is specific and unambiguous.
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 provides explicit guidance on when to use this tool versus alternatives: 'For entities/records use search.' It also explains how to target a specific domain or omit for fan-out, and advises on handling misses by following compute verbs via 'describe'/'call'. This clearly delineates usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
searchSearch the corporaARead-onlyInspect
Search the mounted corpora by query. Routes to each domain's search tool; pass domain to target one. Empty results are logged as gaps. For COMPUTED quantities (molar mass, age/date math, unit conversions) this verb will miss and surface a cross-verb hint (e.g. compute_molar_mass) — follow that hint via describe/call rather than retrying search. Mounted corpora: acupuncture, cocktail, camera, law, copyright, trademark, music-theory, supplements, writing-style, minecraft-dungeons, spanish, medical-denials, languages, behavioral-econ, baseball, agent-practices, pokemon, mcp, readability, citations, relay, models, self-oracle, recall-traps, units, tax, physics, logic, astronomy, biology, geography, medicine, chemistry, calendar, math, eurorack, building-codes, cooking, personal-finance, stardew, coffee, electronics, physiology, diving, decibels, gearing, colorimetry, subnetting, textile-gauge, first-aid, statistics, chess-endgames, woodworking, rating-systems, tuning, check-digits, paper-sizes, wire-gauge, preferred-numbers, swe-claim-denial, psychology, roman-numerals, minecraft-mods, encodings, strength-training, hardiness-zones, terraria, unix-permissions, aspect-ratio, number-bases, resistor-color-code, cognitive-psychology, braille, semver, cron, unicode, timezones, metar, incoterms, soundex, glob, ieee754, http-status, zigbee, uuid, base-encodings, percent-encoding, dms-coordinates, gray-code, hashing, classical-ciphers, hamming-code, geohash, mac-address, poker-hands, capacitor-codes, iso-duration, dice-probability, scrabble-score, wind-chill, mach-number, saffir-simpson, dataviz, patents, chords, dtmf, shoe-size, crc, base58, bech32, base85, reed-solomon, theoretical-ecology, string-similarity, checksums, compression, prng, bloom-filter, computus, hyperloglog, peppers, search-heuristics, tomatoes, solar-times, blood-alcohol, maidenhead-locator, brewing, celestial-navigation, electrochemistry, fluid-mechanics, information-theory, structural-mechanics, regex, combinatorics, graph-algorithms, linear-algebra, psychrometrics, photographic-exposure, photometry, rf-link, screen-resolution, algorithm-complexity, color-names, type-sizes, vin, drill-bit-sizing, iso-country-codes, itu-e164, mime-types, coding-theory, finite-automata, fourier-analysis, numerical-methods, ac-circuits, heat-transfer, markov-chains, orbital-mechanics, currency-codes, elliptic-curves, queueing-theory, totp-hotp, computational-geometry, crockford-base32, html-named-character-references, iana-port-numbers, thermodynamics, acoustics, magnetism, hydrostatics, gas-laws, blackbody-radiation, antenna-gain, bcp47, dimensionless-numbers, iso-language-codes, dns-record-types, midi-messages, kinematics, geometric-optics, digital-logic, convex-optimization, clothing-sizes, knitting-needle-gauge, pipe-size, winemaking-math, ansi-escape-codes, radiation-dosimetry, transmission-lines, nuclear-decay, cribbage-scoring, running-pace, dnd-math, bowling-scoring, tire-size, abn-acn, sedol-cusip, damm-verhoeff, iso-6346, iso-7064, fresnel-equations, hydrogen-spectrum, material-elasticity, pump-affinity, control-theory, em-plane-waves, ordinary-differential-equations, iso-639-reference, posix-signals-reference, quaternions-reference, bayesian-inference, issn-check, ean-barcode, iana-uri-schemes, aquarium-chemistry, 3d-printing, iso-thread, arrow-spine, knitting-needle-sizes, bearing-sizes, camera-film-formats, horology, mechanical-vibrations, rocket-propulsion, fiber-optics, rolling-element-bearing-life, beaufort-scale, iec-60320, iana-protocol-numbers, sae-viscosity, hat-sizes, darts-scoring, complex-numbers, boolean-algebra, game-theory, lambda-calculus, combustion-stoichiometry, bolts-screws, ham-radio-bands, miniature-scale, fracture-mechanics, torsion, catenary, standard-atmosphere, open-channel-hydraulics, gaussian-beam-optics, capillary-action, nato-phonetic, lei, fen-pgn, nmea-0183, phonetic-algorithms, lumber-grades-dimensions, film-speed-iso, telescope-optics, tabletop-rpg-probability, tcr-therapy, software-licenses, z-transform, generating-functions, terzaghi-bearing-capacity, icao-doc8643, imei-reference, gs1-ai, ulid, postal-barcodes, photographic-paper-sizes, gauge-systems-industrial, fishing-line-ratings, sorting-algorithms, candle-making, pool-billiards-geometry, sourdough-ratios, electromagnetic-induction, ring-sizes, probability-distributions, isentropic-flow, fatigue-life, three-phase-power, http-headers, ghs-hazard, abrasive-grit-sizes, cycling-power-zones, group-theory, dynamic-programming-recurrences, molecular-diffusion, smtp-reply-codes, un-locode, chain-pitch, string-gauges, sewing-pattern-grading, tabletop-wargaming-probability, aquaculture-stocking-density, polynomial-arithmetic, matrix-decompositions, nhs-number, diode-junction, elastic-collisions, pressure-vessel, reverberation-time, count-min-sketch, ieee-ethertypes, icao-mrz, http-methods, tls-alerts, bwt-mtf, bicycle-wheel-sizing, silk-thread-nm-denier, soapmaking-lye, iso-3166-2, context-free-grammars, dc-motor-equations, usb-class-codes, punycode, film-frame-rates, aperture-f-stop-series, golf-handicap, hydroponics-nutrients, sewing-fabric-math, resin-mixing-ratios, pdf-structure, piping-water-hammer, hertzian-contact-stress, photovoltaic-cell-performance, un-ece-vegetable-fruit-grading-standards, iata-airport-delay-codes, un-transport-hazard-class-un-numbers, faa-nas-airspace-classes, sieve-mesh-sizing, disc-golf-flight-numbers, beekeeping-hive-math, vinyl-record-cutting-specs, houseplant-light-and-watering-calc, cellular-automata-rules, error-correcting-codes-beyond-block, climbing-rope-and-anchor-ratings, knot-invariants, photovoltaic-cell-model, fiber-dispersion, osmotic-pressure-solutions, faa-n-number, naics-sic-classification, orcid-checksum, swift-bic-format, isni-checksum, shotgun-gauge-and-choke, rope-cordage-strength-and-diameter, screen-mesh-count-and-particle-sizing, battery-cell-form-factor-codes, xor-filter, kite-line-and-wind-window, clothing-glove-size-standards, wasm-module-header, protobuf-wire-format, rankine-cycle-efficiency, projectile-ballistics-drag-corrected, faa-airport-codes, aes-fips-block-parameters, voronoi-delaunay, iso15459-license-plate, np-completeness-reductions, hidden-markov-viterbi, png-ihdr-fields, mbr-partition-table, fuzzywuzzy-rapidfuzz-string-similarity-api-reference, v-belt-sprocket-sizing, e164-carrier-mnc-mcc, faa-nav-aid-frequency-bands, go-baduk-scoring, zip-central-directory-header, curling-scoring, mahjong-hand-scoring, sudoku-difficulty-rating, dominoes-scoring, base45, typography, tides, pbkdf2, ndc, epsg, hkdf, hvac-duct-sizing, hts, elevator-rope-crane-wire-rope-classification, board-game-elo-scoring, ecfr, tide-and-moon-phase-almanac, regular-expression-derivatives, obd2-pids, emission-designators, runway-designators, qr-code, iban-structure, sewing-needle, experiment-design, iana-link-relations, scientific-method, mtg-rules, crystallography.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to search for. | |
| domain | No | Optional: restrict to one domain. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, it discloses that empty results are logged as gaps, it routes to domain-specific tools, and for computed quantities it surfaces a hint rather than returning results.
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?
Front-loaded with key behavioral info, but the massive list of domain names is verbose and unnecessary for tool selection. Could be summarized or referenced externally.
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?
Covers routing, domain restriction, empty result handling, and computed quantity hint. Missing output structure details, but given the complexity and absence of output schema, it is fairly complete.
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 coverage is 100% with clear descriptions for query and domain. The description adds context about routing behaviors but does not significantly enhance meaning beyond the schema.
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 states it searches mounted corpora by query and routes to domain-specific search tools. It distinguishes from siblings like 'lookup' and 'compute' by explicitly noting it will miss computed quantities and provides a cross-verb hint.
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?
Explicit when-to-use and when-not-to-use guidance: use for general search, but for computed quantities (molar mass, etc.) it will miss, so follow the hint to describe/call instead. Also mentions optional domain parameter to restrict search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verifyVerify claims against sourcesARead-onlyInspect
Check claims against the corpora. SINGLE: verify({claim}) grounds one claim (core/verify truth-referee verdict where a domain surfaces it, else a corpus-grounding badge). RECEIPT: verify({claims:[…]}) claim-CHECKS each assertion and returns a TYPED per-claim verdict (verified / corrected / abstained) + drilled value + source, as a structured receipt (rides the response → portable to any client). Each claim is graded one of two ways: RECOGNITION-FREE — give op + params + asserted (STATE the computation you ran; it is RE-EXECUTED with no catalog match, so it grades NOVEL inputs too — the strongest form), or CATALOG-MATCH — give claim + asserted (matched to a covered record). Pass asserted (your own answer) to have it GRADED, not just grounded — the receipt corrects a confidently-wrong claim the model can't catch itself. A claim with no receipt line is unverified.
| Name | Required | Description | Default |
|---|---|---|---|
| op | No | Recognition-free single check: the computation you performed (e.g. 'compare_decimal'). Discover ops via the recall-traps check_claim verb (no args). | |
| claim | No | A single claim to check (back-compat / catalog-match). For several, use `claims`. | |
| claims | No | Receipt mode: the claims to check. Each item is {claim?, op?, params?, asserted?, domain?} (or a bare string). | |
| domain | No | Optional: restrict to one domain. | |
| params | No | Recognition-free single check: inputs for `op`. | |
| asserted | No | With a single `claim`/`op`: your answer, graded against the re-executed truth. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that claims are re-executed and graded, and explains the return format (structured receipt). Annotations confirm read-only behavior. No contradictions. It adds context beyond annotations, though could mention more about error handling.
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 verbose and densely technical, using jargon like 'recognition-free' and 'catalog-match' without immediate clarity. While it is well-structured with labeled sections, it could be more concise to improve readability for an AI agent.
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?
Given the complex input schema with nested objects and multiple modes, the description thoroughly covers usage patterns, parameter relationships, and output behavior. It explains what happens when no receipt line is present, ensuring the agent understands the tool's full capability.
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 coverage is 100%, providing baseline. The description adds significant meaning: it explains the difference between single and receipt mode, the role of 'asserted' for grading vs grounding, and clarifies that 'op' and 'params' are for recognition-free checks. This exceeds minimal expectations.
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 explicitly states the tool's purpose: 'Check claims against the corpora' and distinguishes between two modes (SINGLE and RECEIPT) with clear outputs. It differentiates from sibling tools by focusing on verification with typed verdicts.
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 provides clear guidance on when to use single vs receipt mode and explains the two grading methods (recognition-free vs catalog-match). It hints at discovering available ops via another verb, but does not explicitly state when not to use this tool or compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!