analyze_memory

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so no safety disclaimer is needed from the description. The description adds useful behavioral scope by naming the evidence dimensions analyzed (peak, retained-end, allocation), which complements the annotation-provided safety profile. It does not discuss sorting or pagination, but that is a minor gap given the strong annotations.

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 compact sentence that front-loads the verb and resource and then enumerates the key evidence categories. There is no filler, redundancy, or restatement of the tool name.

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 a nested query object and many related analyze/extract siblings, the description is somewhat thin: it does not mention that the memory profile must already be extracted, nor when to prefer this over extract_memray/get_extraction. The rich input schema and annotations carry a lot of weight, but the missing selection context keeps this from being fully complete.

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 descriptions already cover the two required parameters: limit and run_or_artifact. The tool description adds loose semantic hints connecting 'peak', 'retained-end', and 'allocation' to the MemoryAllocationView enum values, but it does not explain the query object's filtering or ranking options. At 67% schema coverage, the description partially compensates but leaves the query behavior largely to the schema.

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: 'Analyze memory-profile runs or artifacts'. It further narrows the purpose to 'peak, retained-end, and allocation evidence,' which clearly separates it from the many analyze_* siblings that target CPUs, GPUs, PyTorch, failures, or scaling.

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 gives no guidance on when to use this tool versus related siblings like extract_memray, get_extraction, or other analyze_* tools. It does not state prerequisites, exclusions, or conditions under which a sibling should be chosen instead. Some context is implied by the word 'memory-profile,' but no explicit routing is provided.

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