plith

burnrate_track

Idempotent

Log the actual cost of an LLM call after execution. Call this after every LLM request to build calibration data that improves burnrate_estimate accuracy over time. Free — no credits charged. Returns the recorded cost entry with computed margin versus the prior estimate when one exists for this model and token range.

Input Schema

TableJSON Schema

Name	Required	Description
`model`	Yes	Model identifier as returned by the provider. Examples: claude-sonnet-4-6, gpt-4o, gemini-2.0-flash, mistral-large-latest. Unknown models are accepted but cost may show as $0.
`task_id`	No	Optional task ID for cross-referencing spend with DedupQ deduplication results. Use the same task_id passed to dedupq_check to link cost tracking with deduplication.
`provider`	Yes	LLM provider identifier. Supported: anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Must match the provider of the model used.
`input_tokens`	Yes	Actual prompt tokens used. Must be >= 0.
`output_tokens`	Yes	Actual completion tokens used. Must be >= 0.
`cache_read_tokens`	No	Optional. Cache-read tokens.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`model`	No
`tracked`	No
`provider`	No
`record_id`	No
`request_id`	No
`credits_used`	No
`input_tokens`	No
`output_tokens`	No
`pricing_found`	No
`actual_cost_usd`	No
`credits_remaining`	No
`fallback_behavior`	No
`actual_cost_usd_formatted`	No

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare idempotentHint=true and destructiveHint=false. The description adds valuable context beyond these: 'Free — no credits charged' and 'Returns the recorded cost entry with computed margin versus the prior estimate,' disclosing both cost implications and return behavior. This is a good supplement to 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?

Three sentences, each serving a distinct purpose: action, usage guidance, and return behavior. Information is front-loaded, concise, and free of fluff or repetition.

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 simplicity, the description covers the essential aspects: what it does, when to use it, return value, and cost. The output schema exists, so return details are further specified. No significant gaps remain for an agent to select and invoke the tool 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 coverage is 100% with detailed descriptions for all parameters. The description adds meaning by mentioning 'this model and token range' when computing margins, linking the parameters (model, input_tokens, output_tokens) to the tool's estimation logic. This provides extra 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 clearly states the action with a specific verb and resource: 'Log the actual cost of an LLM call after execution.' It distinguishes from sibling tools like burnrate_estimate by positioning this as recording actuals for calibration, and the title 'Record actual LLM spend' reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage timing: 'Call this after every LLM request to build calibration data.' It references burnrate_estimate as the beneficiary of the data, implying an alternative use case (estimating vs. recording). However, it does not explicitly state when NOT to use the tool or name alternatives directly.

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

All plith 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

A4.4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose, grouped by functionality (cost, dedup, guardrails, pitfalls, quality, rigor). Descriptions clearly differentiate within groups, so an agent can reliably select the correct tool.

Naming Consistency5/5

All tool names follow a consistent pattern of lowercase with underscores, using category prefix (burnrate_, dedupq_, guardrail_, etc.) followed by a descriptive verb or noun. No naming mix-ups.

Tool Count5/5

15 tools cover multiple distinct capabilities (cost management, deduplication, guardrails, pitfalls, quality, workflows) without being excessive. Each tool has a clear role, and the count is appropriate for the server's scope.

Completeness4/5

The tool surface covers core workflows well, but there are minor gaps: no tool to delete/update guardrail policies, no explicit qualitygate rule management, and no workflow cancellation tool. Also, 'qualitygate_trends' is referenced but not provided as a tool. Overall, agents can work around these gaps.

Resources

Need Help?