memory_recall

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

With no annotations, the description carries the full burden. It discloses that the tool searches persistent memory at a specific path and is for recalling insights. However, it does not explicitly state that the operation is read-only, nor describe behavior when no matches are found or whether any local indexing is involved. This is adequate but has gaps.

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 short and front-loaded with the core purpose, followed by the storage location and a clear usage cue. It's efficient, though the first two sentences are slightly redundant ('Recall' vs 'Searches'). Still, every sentence 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 simple 1-parameter tool with an output schema, the description covers the essential information: what it searches, where, and when to use it. It doesn't explain return format, but the output schema handles that. It could mention limitations or fallback behavior, but overall it's complete enough.

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% with a helpful description and examples for 'query'. The description itself does not add much beyond the schema, but the baseline is 3 due to complete schema coverage. It reinforces the nature of the query ('matching patterns and insights') but doesn't provide additional semantic details.

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 states the tool's function: 'Recall insights from past debugging sessions' and 'Searches the agent's persistent memory (~/.x64ai/)'. This gives a specific verb, resource, and scope. It distinguishes from most sibling tools by targeting persistent memory, though it doesn't explicitly differentiate from session_search.

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?

Provides an explicit 'USE WHEN: starting analysis on a new binary — past insights may apply.' This gives a clear context for when to invoke the tool. It lacks explicit 'when not to use' or alternative tool references, so it doesn't reach level 5.

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