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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so no safety disclosure is needed. The description adds beyond annotations by specifying the warning behavior ('Warns if budget exceeds model context window') and model coverage ('Supports 25+ models'), which are useful behavioral traits not present in annotation fields.

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 sentences, front-loaded with the core action, no redundancy. Every word earns its place, and the warning/model support details are valuable additions without bloat.

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?

The tool has 8 parameters and an output schema, so the description doesn't need to detail returns. It covers the core behavior and key constraints (warning, model support). However, it lacks explicit guidance on how it differs from closely related siblings (count_tokens, context_window_check, llm_fit_finder), which would make it fully complete for an agent operating in a crowded tool space.

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 description coverage is 100%, so each parameter is already explained. The description adds semantic meaning by grouping parameters into logical categories ('system prompt, user input, context/RAG chunks, and expected output') and implicitly clarifying that the tool can accept both raw text (to estimate tokens) and manual token counts. This goes slightly beyond the schema's individual field descriptions.

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 states a specific verb and resource: 'Plan token allocation across system prompt, user input, context/RAG chunks, and expected output.' It clearly distinguishes from siblings like count_tokens and contextualize by focusing on planning allocation across multiple components, not just counting or checking.

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?

The description implies when to use it (planning allocation across multiple segments) and mentions warning behavior, but does not explicitly name alternatives or exclusions. In a crowded sibling space (count_tokens, estimate_llm_cost, context_window_check), it would benefit from explicit 'use this when' guidance, though the purpose is clear enough to infer intended use.

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