Agent Memory

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

Annotations declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, so the description doesn't carry the full safety burden. The description adds the pricing note (2 MESH/call), which is useful cost transparency not in annotations. However, it doesn't clarify whether 'store' writes over existing memories, how scoping works, or what recall returns — leaving behavioral questions unanswered beyond what annotations already imply.

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 compact at roughly two sentences, but it includes marketing-style phrases ('The primitive shallow builders lack') and a pricing tag that, while informative, feels promotional and not technical. The core functional sentence is efficient, but the self-promotional framing takes space that could clarify behavior. Reasonably concise but not tightly structured.

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 two-action (store/recall) tool with a nested object, 100% schema coverage, and three annotations, the description covers the essentials but is thin on practical details. It doesn't say what recall returns (results format), whether storage is global or per-workspace, or how 'scoped' memory behaves. Given no output schema, the description should disclose more about what the agent can expect back from a recall call, making this incomplete but not inadequate.

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% — the schema itself documents the 'query', 'action', and 'content' parameters with descriptions and the action enum. The description adds the insight that recall is 'by meaning' (semantic rather than keyword), which adds value beyond the schema. But the description doesn't deepen parameter understanding significantly; it's a baseline 3 with slight credit for the semantic-recall clarification.

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 this is persistent, scoped memory for storing and recalling 'by meaning', which clearly identifies the purpose as a semantic memory store. It distinguishes itself from 'shallow builders' by contrast, though it doesn't name a specific sibling alternative. The verb 'store and recall' plus the resource 'agent memory' is clear enough.

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 when to use it (when you need persistent semantic memory) and contrasts with shallow builders, but it offers no explicit guidance on when NOT to use it or what alternatives exist among the many sibling tools (task-analysis, agent-brain, structured-extract). The 'scoped' mention hints at constraints but doesn't explain what scope means or how it differs from agent-brain or task-analysis.

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