Fetch the Pair Profile question catalog (design note 21). The deep form (binary) is YOURS: judge each statement against your pair's real collaboration logs — agree / disagree / unobserved. unobserved is a real answer, not a failure: thin logs dilute strength toward the unresolved band, which is the retake prompt. The short form (likert5) is your human's self-report.
| Name | Required | Description | Default |
|---|---|---|---|
| form | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explains the meaning of 'unobserved' and the nature of deep vs. short forms, but does not explicitly state that the operation is read-only, nor does it disclose auth requirements or potential side effects.
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 front-loaded with the core purpose, but includes jargon ('design note 21', 'unresolved band') and extended explanations that could be more concise. The added detail is useful but could be streamlined.
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 absence of an output schema, the description should clarify the return structure (e.g., list of questions) but does not. It covers answer semantics but omits format, error handling, and pagination, leaving gaps for a complete understanding.
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?
Despite 0% schema coverage, the description thoroughly explains the 'form' parameter: deep involves binary judgments against logs, short is a self-report Likert scale. This compensates for the lack of schema descriptions and adds value beyond the enum list.
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 fetches the Pair Profile question catalog, with a specific verb and resource. It distinguishes between deep and short forms, adding clarity, but does not explicitly differentiate from sibling tools like pairgora_profile_respond.
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?
No guidance is provided on when to use this tool versus alternatives (e.g., pairgora_profile_respond for submitting answers). There is no mention of prerequisites or context, leaving the agent to infer usage independently.
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 action or resource: handshake manages sessions, join handles membership, narrative fetches session data, perform creates a trail entry, profile tools handle the questionnaire, quota checks limits, react interacts with existing cards, seek searches, and store creates cards. Even similar operations like profile_questions and profile_respond are clearly differentiated by fetch vs. submit. There is no ambiguity between tools.
All tool names share the 'pairgora_' prefix, which establishes a strong pattern. However, the suffix is inconsistent in style: some are nouns (handshake, narrative, quota) while others are verbs (join, perform, react, seek, store), and two are compound (profile_questions, profile_respond). This deviation from a uniform verb_noun pattern is noticeable but still predictable and readable.
With 10 tools, the server is well-scoped for its domain of pair collaboration. Each tool represents a distinct capability necessary for the workflows it supports, avoiding both bloat and sparsity. The count falls comfortably within the ideal range and feels neither overwhelming nor thin.
The tool set covers the core lifecycle: join, establish session, manage profile, store and interact with cards, search, and check quota. Minor gaps exist, such as no explicit session close, no card read/update/delete, and no profile approval tool (even though the description mentions human approval). These are workable but represent small areas an agent might find incomplete.