Rank candidate dysfunctions matching the observed behaviours. Returns scored candidates with matched_in (which field matched) for transparency. The base package uses field-weighted keyword search. The optional embeddings extra adds cosine re-ranking.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| observations | Yes | Observed behaviours, symptoms, or log patterns. | |
| modality_hint | No | Optional hint about which modality the observations come from. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / additionalPropertiesAdded value: +falseInput schema / properties / limit / maximumAdded value: +20Input schema / properties / limit / minimumAdded value: +1Input schema / properties / modality_hint / maxLengthAdded value: +100Input schema / properties / observations / items / maxLengthAdded value: +2000Input schema / properties / observations / items / minLengthAdded value: +1Input schema / properties / observations / items / patternAdded value: +"\\S"Input schema / properties / observations / maxItemsAdded value: +50Input schema / properties / observations / minItemsAdded value: +1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the return format (scored candidates with matched_in) and the two scoring modes (keyword vs embeddings), adding transparency beyond the schema. However, it does not mention any side effects or safety implications, though a diagnosis tool is likely read-only.
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?
Three sentences, front-loaded with the primary purpose, followed by output format and algorithmic detail. No extraneous information. Highly concise and well-structured.
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 no output schema, the description explains the return value (scored candidates with matched_in) and the scoring mechanism. It covers the essential behavior for an agent to call the tool correctly. It doesn't discuss edge cases or parameter behaviors, but those are sufficiently covered by the schema. The description is complete enough for a moderate-complexity tool.
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 67% (observations and modality_hint have descriptions, limit does not). The description adds no additional detail about parameter syntax or constraints beyond what the schema provides. It does mention 'matched_in' which is an output field, not a parameter. The moderate coverage means the description doesn't need to compensate heavily, so a 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 clearly states a specific verb ('Rank') and resource ('candidate dysfunctions') and clarifies the output (scored candidates with matched_in). It distinguishes from siblings by focusing on ranking based on observed behaviours, which is unique among the listed tools.
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 explains the underlying search algorithm (field-weighted keyword vs embeddings) but does not explicitly state when to use this tool over alternatives like get_differential_map or get_dysfunction. It provides context but lacks explicit when/when-not guidance, leaving the agent to infer the appropriate use case.
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.
Each tool targets a distinct aspect of the domain: diagnosis, mapping confusions, retrieving entries, elicitation probes, listing axes/dysfunctions/compromised entries, ID resolution, statistics, severity, and interventions. No two tools overlap in purpose; descriptions clearly differentiate them.
Most tools follow verb_noun pattern (get_*, list_*, resolve_id, score_severity, suggest_intervention), but differential_diagnosis and review_stats deviate (noun-like phrases). The inconsistency is minor and doesn't obscure meaning.
11 tools is well within the ideal 3-15 range. Each tool serves a distinct purpose in the diagnostic workflow, and none feel redundant or missing for the stated domain.
The surface covers listing, retrieval, differential diagnosis, probes, severity, interventions, stats, and ID resolution. Minor gaps exist (e.g., no tool to add/update entries or directly compare two dysfunctions), but these are outside the apparent read-only research scope.