Skip to main content
Glama

sniff-mcp

by world.sniff

ask_the_graph

THE INSTRUMENT — ask a free-form CROSS-SPECIES genetics question and get FILTERED, HONEST HINTS (never a confident guess). It compiles your question into a typed query plan over the dog<->human edge-graph, runs it deterministically, and scores each answer PATH by its weakest edge — returning ranked hints with an evidence TIER (fact / computational / inferred) + citations, or an honest ABSTAIN with a demand signal when the graph can't answer. BEST FOR model-discovery / translational traversal: 'which dog breeds or genes model human ', 'what is the dog ortholog of ', 'what dog disease is phenotypically like '. Answers are HYPOTHESIS-GENERATING, not clinical claims: a fact hint = an OMIA-curated model-of; a computational hint = a conserved 1:1 dog ortholog (a candidate — never 'dogs get this disease'); inferred = shared cross-species phenotype. Returns {plan (what it asked the graph), hints:[{answer, tier, score, path (the cited edges), weakest_edge, provenance}], abstain, demand_signal}. Set narrate=true for a gated one-line prose summary per hint (faithful-or-honest-template; it can never fabricate). Use ask instead for owner-facing breed/disease/carrier questions; use THIS for human-disease -> dog-model cross-species queries.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
narrateNo
questionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.9/5.0
Behavior5/5

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

No annotations are provided, so the description fully discloses behavioral traits: it returns filtered, honest hints, never a confident guess; uses a deterministic query plan; scores by weakest edge; provides evidence tiers; abstains when can't answer; and is hypothesis-generating.

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?

The description is verbose but informative; it front-loads key information and uses capitalization for emphasis. While not extremely concise, every sentence adds value.

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?

Given the tool's complexity (graph-based, multiple evidence tiers) and the presence of an output schema, the description fully covers purpose, usage, behavior, parameters, and output format, making it complete.

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

Parameters5/5

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

Schema coverage is 0%, but the description compensates well: it explains that 'question' is a free-form cross-species genetics question, and 'narrate=true' provides a one-line prose summary per hint with specific behavior.

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?

The description clearly specifies the tool's purpose: asking cross-species genetics questions about dog-human diseases, and explicitly distinguishes from sibling tool 'ask' for owner-facing breed/disease queries.

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?

The description provides explicit guidelines: best for model-discovery and translational traversal, and advises using 'ask' for owner-facing breed/disease/carrier questions.

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

All sniff-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Tools are mostly distinct with clear purposes, but some overlap exists between disease-related tools (disease_lookup vs disease_links) and between ask and ask_the_graph. Descriptions help differentiate, but an agent might still misselect.

Naming Consistency2/5

Naming patterns are inconsistent: some tools use verb_noun (ask, search_diseases), others use noun_noun (breed_similarity, disease_bridge), and some use descriptive phrases. No consistent convention observed.

Tool Count5/5

18 tools is well-scoped for a canine genetics knowledge base. Each tool serves a distinct function covering breed, disease, variant, and query capabilities without being overwhelming.

Completeness5/5

The tool set covers all major aspects of the domain: breed profiles, disease lookup with links, variant querying, semantic search, and metadata. No obvious gaps for the stated educational purpose.

Resources