Announce upcoming heavy GPU, CPU, or RAM work so other agents can plan around it without reserving resources; set done=true to remove a project's plans.
Announce heavy work later so others plan around it (reserves nothing). done=true removes your project's plans.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | HH:MM or now | |
| done | No | Remove | |
| what | No | What | |
| gpu_pct | No | GPU % | |
| minutes | No | Minutes | |
| project | No | Project | |
| vram_gb | No | VRAM GB |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose two important behaviours: the plan reserves nothing, and done=true deletes the project's plans (a broader blast radius than a single record). It omits confirmation of idempotency, permissions, and what happens when all seven optional parameters are omitted. Useful but incomplete for an unannotated mutation tool.
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?
Two short sentences, front-loaded with the core purpose before the done=true deletion caveat. No wasted words, though the terseness edges toward under-specification rather than elegant brevity.
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?
For a seven-parameter, unannotated tool with no output schema, the description leaves major gaps: what a 'plan' is, default values, which parameters are meaningful together, and what the call returns. It never states that all parameters are optional or what an empty call does. An agent could invoke it correctly only by guessing.
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 nominally 100%, so the baseline of 3 applies, but the schema descriptions are extremely thin ('What', 'Remove', 'Project'), adding little real meaning. The description does clarify done=true's effect at project scope and implies 'at' is a time-of-day or 'now'. Nothing explains how at, minutes, gpu_pct, and vram_gb interact.
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 gives a specific verb and resource: announcing future heavy work so others can plan around it, plus a removal mode via done=true. The parenthetical 'reserves nothing' implicitly separates it from firefighter_submit, though it never names that sibling directly. The dual create/delete behaviour in one tool slightly blurs the single stated purpose.
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?
It says the tool is for announcing work 'later', and that done=true removes plans, but gives no explicit when-to-use versus firefighter_submit, firefighter_job, or firefighter_wait, and no exclusion or prerequisite guidance. Routing is left entirely to inference from the tool names. An agent could easily confuse this with actually submitting work.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.