memoryguard_extract_memories

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, and it delivers: 'read-only preview' and 'Does NOT write to shared memory' explicitly disclose non-mutation, and 'authorized source root' signals permission constraints. It could add detail on error behavior for unauthorized paths or file-size limits, but the safety profile is clearly conveyed beyond what structured fields provide.

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?

Three sentences with zero waste: purpose and scope, return shape, then the non-write declaration and sibling routing. The primary verb and resource are front-loaded, and every sentence earns its place by conveying information not available elsewhere in the structured data.

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 no output schema and no annotations, the description covers the key gaps: what it returns (kind, risk_level, preview), that it is non-destructive, and what the follow-up tool is. Minor gaps remain—preconditions like whether the source must already be registered, and error behavior for unauthorized paths—but the essentials an agent needs to call it correctly are present.

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 the baseline is 3. The description marginally reinforces source_path semantics by repeating the 'authorized source root' constraint, but it adds no new meaning for either parameter beyond what the schema already documents. There is no genuine compensation needed or provided.

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+resource: 'Extract memory segments from a source file under an authorized source root.' It also describes the return value (candidate list with kind, risk_level, preview) and explicitly differentiates itself from siblings by declaring 'Does NOT write to shared memory' and pointing to memoryguard_accept_candidates for the write path. An agent can distinguish this from the 50+ siblings without opening the schema.

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 provides clear context ('read-only preview') and explicitly routes to an alternative: 'Use memoryguard_accept_candidates to write accepted candidates.' This names a sibling and the condition selecting it. However, it lacks explicit when-not-to-use guidance or differentiation from other preview-like siblings (e.g., memoryguard_import_preview, memoryguard_history_extract_preview), so it stops short of a 5.

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