memoire

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it reads from an in-memory usage tracker, returns zero values if no AI calls have been made, specifies the return structure on success, and details error behavior (never throws, returns a zero-value object with a specific message if ANTHROPIC_API_KEY was not set). This covers most behavioral aspects, though it could mention rate limits or performance characteristics.

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?

The description is well-structured and front-loaded with the core purpose, followed by prerequisites, return values, error behavior, and usage guidelines. Each sentence earns its place by providing essential information without redundancy, making it efficient and easy to parse.

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?

Given the tool's complexity (simple read operation with no parameters) and the absence of annotations and output schema, the description is complete. It covers purpose, prerequisites, return structure, error handling, and usage scenarios, providing all necessary context for an AI agent to invoke the tool correctly without relying on structured fields.

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?

The tool has 0 parameters with 100% schema description coverage, so the baseline is 3. The description adds value by explaining that no parameters are needed ('Prerequisites: None — reads from the in-memory usage tracker'), which clarifies the tool's operation beyond the empty schema. However, it doesn't need to compensate for any parameter gaps, so a 4 is appropriate for adding useful context.

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 clearly states the specific action ('Get AI token usage and estimated cost') and resource ('current MCP server session'), distinguishing it from siblings like 'get_tokens' (likely design tokens) and 'get_specs' (design specifications). It precisely defines what the tool does without being vague or tautological.

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 explicitly states when to use this tool ('to monitor token spend during a session involving analyze_design, design_doc, or compose calls, to estimate costs before running large batch operations, or to audit which tools are the heaviest AI consumers in a workflow'), providing clear context and alternatives. It also mentions prerequisites ('None') and distinguishes it from other tools by focusing on AI usage tracking.

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