mdan_memory_recall

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

The description is consistent with the readOnlyHint=true annotation (recall is a read operation), so there is no contradiction. It adds useful behavioral context beyond annotations: results are scoped to previous sessions and ordered by confidence. However, it does not disclose failure modes (e.g., empty results), whether the search is fuzzy or exact, or the response format; with the safety profile already covered by annotations, a mid score is appropriate.

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?

A single sentence that front-loads the primary outcome (recall) and packs in scope ('from previous sessions') and ordering ('highest confidence first') without waste. Every word earns its place.

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 4-parameter retrieval tool with no output schema and a confusingly similar sibling (mdan_memory_list), the description omits important information: how this differs from memory_list, what the type filter values mean, and what the caller receives back. The core calling pattern (agent required, optional filters) is inferable, but the gaps are material for correct tool selection and invocation.

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 only 25% (only 'query' is described), so the description must compensate. It partially does: 'an agent's memories' clarifies that 'agent' identifies whose memories are retrieved, and 'highest confidence first' explains result ordering. However, the meaning of the 'type' enum (observation, preference, context, decision) is left entirely to inference, and 'limit' behavior is not contextualized.

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 names a specific verb (recall) and resource (an agent's memories from previous sessions), plus a distinguishing ordering trait (highest confidence first). It is clearly a read/retrieval operation, differentiating it from siblings like mdan_memory_remember and mdan_memory_forget, though it does not explicitly differentiate from mdan_memory_list.

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?

No guidance is given on when to use this tool versus the closely related mdan_memory_list, which also retrieves memories, or mdan_consult_agent. There are no stated exclusions, prerequisites, or selection conditions, so an agent must infer appropriateness from the tool name alone.

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