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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds meaningful behavioral nuance: it explicitly states the server never requests samples/notes/indicators and instructs the AI to keep data local. It also clarifies that the 'profile' parameter annotates rather than filters, which is a non-obvious behavior.

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 main purpose, followed by return content and then parameter clarification. Each sentence serves a distinct purpose, though it is somewhat long and could be trimmed without losing meaning.

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 no output schema, the description adequately covers what the JSON payload contains (section guidance, MBC, ICD-203, Pyramid-of-Pain, briefPolicy) and how the profile parameter behaves. It also provides essential privacy context. This is complete enough for an agent to decide when and how to invoke the tool.

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 the baseline is 3. The description adds extra semantic value by explicitly explaining that 'profile' annotates sections rather than filtering, resolving a potential interpretation ambiguity. Other parameters like topics and detail_level are already well-described in the schema, so no further compensation is needed.

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 identifies the tool as loading Lenny Zeltser's malware analysis report writing context for local analysis, which is a specific verb+resource pairing. It further lists the distinct contents (MBC model, ICD-203 confidence, Pyramid-of-Pain, briefPolicy) that distinguish it from sibling tools like malware_get_template or malware_get_guidelines.

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 states the tool is for 'local analysis' and emphasizes that it does not request sensitive data, implying it is a safe context loader. However, it does not explicitly contrast with alternatives like malware_get_guidelines or malware_get_template, so the usage context is clear but exclusion criteria are only implied.

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