Audit memory value

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing the safe, non-mutating nature. The description adds value by detailing what behavioral aspects it measures (capture-to-recall behavior, duplicate rate, stale raw hits), which is context beyond the annotations. It does not contradict any annotation and provides a clearer picture of the tool's analytical focus, though it stops short of describing output structure or side effects.

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 a single, information-dense sentence that front-loads the primary action ('Measure') and lists the key metrics immediately. There is no filler or repetition. It earns every word and remains easily scannable, ideal for an AI agent parsing tool definitions.

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 tool with three parameters, no output schema, and zero schema coverage, the description leaves critical gaps. It lists what metrics are measured but does not specify the return format, how parameters affect the results, or what constitutes a valid invocation. An agent cannot confidently construct a request without additional external knowledge. The complexity is moderate, but the lack of parameter and output documentation makes this incomplete.

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 0%, so the description must compensate for the three parameters (days, tags, namespace). It does not explain what these parameters control or how they influence the audit. The parameter names are somewhat intuitive, but without semantic detail an agent cannot determine how to set values to achieve a desired audit scope. This is a significant gap given no output schema exists either.

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 ('Measure') with a clear resource ('memory') and enumerates concrete metrics (capture-to-recall, unused records, recall age, etc.). It also explicitly distinguishes itself by noting 'without changing memory,' which sets it apart from mutation tools like update_memory or delete_memory. This gives an agent an unambiguous understanding of the tool's 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?

The description implies a usage context (auditing memory metrics) but does not explicitly state when to prefer this over siblings like get_memory_snapshot or search_memory. It lacks a 'when not to use' or alternative tool references, leaving the agent to infer that this is for analytical insights rather than retrieving raw data. The phrase 'without changing memory' hints at a read-only analysis use case, but no direct routing guidance is provided.

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