Token usage vs context window. Returns status (ok/warn/critical) and recommendation (ok/compress/fracture).
Token usage vs context window. Returns status (ok/warn/critical) and recommendation (ok/compress/fracture).
| Name | Required | Description | Default |
|---|---|---|---|
| messages | No | Current conversation messages [{role, content}] | |
| max_tokens | No | Claude context window size. Default 200000. | |
| reserve_tokens | No | Headroom reserved for the response. Default 10000. |
Changes observed during successful MCP inspections.
v0.8.4Input schema / properties / messages / itemsAdded value: +{
+ "properties": {
+ "content": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ }
+ ],
+ "description": "Message text, or a list of content blocks ({type: text, text})."
+ },
+ "role": {
+ "description": "user | assistant | system",
+ "type": "string"
+ }
+ },
+ "required": [
+ "content"
+ ],
+ "type": "object"
+}v0.8.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It helpfully discloses the return categories (status ok/warn/critical, recommendation ok/compress/fracture), which is real information. But it says nothing about side effects, whether it is read-only, or how the thresholds are determined.
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 purpose and then the outputs. Every clause earns its place with no filler.
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?
There is no output schema, so the description minimally covers return values, and the simple 3-param computation is otherwise self-evident. But given the dense sibling namespace, a bare purpose line leaves the agent without enough to reliably select this tool over near-neighbors.
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 100%, so all three parameters (messages, max_tokens, reserve_tokens) are already documented with types, defaults, and descriptions. The description adds no parameter-level meaning beyond the schema, so the baseline 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?
States the resource and computation clearly ('token usage vs context window') and names the two result fields, so an agent knows this is a budget-assessment tool. However, it does not distinguish itself from siblings like chimera_budget_lock, chimera_compress, or chimera_fracture, which an agent could easily confuse for the same job.
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?
There is no guidance on when to call this versus alternatives. With ~50 siblings including chimera_budget_lock, chimera_compress, and chimera_cost_track, the agent gets no signal about which to pick or in what order. Only implied usage is available.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.