Kamy

Record LLM call (Kamy Trace)

trace_record

Record one LLM call — prompt, output, provider, model, tokens, latency — into Kamy Trace, a signed retention ledger. Each record is hashed and signed at write time, so it can be produced later without the 'you could have edited this' objection. Reach for it when model calls need a reviewable history: regulated workflows, customer-facing generations, anything you may have to explain months later. Set status 'flagged' with status_detail on calls a human should revisit. Returns { id, content_sha256, signature, recorded_at, verify_url }. Requires a Kamy API key with the trace:record scope; each call consumes monthly Trace quota.

Input Schema

TableJSON Schema

Name	Required	Description
`tags`	No	Up to 20 free-form labels. trace_search can filter on any one of them.
`model`	Yes	Model identifier exactly as the provider reports it, e.g. 'claude-sonnet-4-6'.
`output`	No	The model's response, verbatim. Any JSON value.
`prompt`	No	The prompt / request you sent, verbatim. Any JSON value (string, array, object).
`status`	No	Outcome. 'flagged' marks a call you want a human to review later. Defaults to 'ok'.
`feature`	No	Product area the call belongs to, e.g. 'support_reply'. Filterable in trace_search.
`provider`	Yes	Which model vendor served the call. Use 'custom' for anything self-hosted.
`latency_ms`	No	Wall-clock duration of the call.
`input_tokens`	No	Prompt tokens billed.
`output_tokens`	No	Completion tokens billed.
`status_detail`	No	Why the call was flagged or failed. Free text.

TDQS

A4.9/5.0

Behavior5/5

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

Beyond annotations, discloses that each record is hashed and signed at write time for non-repudiation, describes the return shape ({id, content_sha256, signature, recorded_at, verify_url}), and states auth requirements (API key with trace:record scope) and quota consumption. No contradiction with annotations.

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

Conciseness5/5

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

Succinct yet comprehensive paragraph. Front-loaded with core purpose, followed by unique trait (signing), usage guidance, parameter hint, return type, and auth/quota. Every sentence adds value without redundancy.

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 11 parameters and no output schema, the description covers the essential: purpose, signing feature, use cases, return fields, auth, and quota. Combined with 100% schema documentation, it provides a complete picture for an AI agent to select and invoke correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3, but the description adds extra meaning: e.g., 'Set status flagged with status_detail on calls a human should revisit' for status parameter, and tags are 'filterable in trace_search'. Adds situational context beyond the schema.

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 states the tool records one LLM call with specific fields into Kamy Trace, a signed retention ledger. It clearly differentiates from siblings like 'trace_search' and 'record_agent_action' by emphasizing the LLM call recording and cryptographic signing.

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?

Explicitly advises when to use the tool: 'Reach for it when model calls need a reviewable history: regulated workflows, customer-facing generations, anything you may have to explain months later.' Also explains setting status flagged for human review, and mentions required API key and quota.

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

All Kamy tools Inspect

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

A4.2/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose with detailed descriptions that differentiate similar tools (e.g., render_pdf vs render_async vs render_batch, create_signature_request vs create_envelope). No two tools overlap in a way that would cause confusion.

Naming Consistency5/5

All tool names follow a consistent lower_snake_case verb_noun pattern (e.g., attest_artifact, convert_document, list_renders). No mixing of conventions or ambiguous verb choices.

Tool Count4/5

47 tools is high but reflects the broad scope of the platform (document generation, signing, auditing, scheduling, webhooks, verification). Some informational tools could be merged, but the count is still reasonable for the domain.

Completeness3/5

The tool set covers the core document lifecycle well but has notable gaps: no tool to delete renders, no tool to void/cancel signature requests, and no CRUD for templates (only list and schema). The inability to pause schedules via MCP is also a gap.

Resources

Need Help?