agent_memory

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

With no annotations provided, the description carries full burden for behavioral transparency. It successfully explains available actions (link/recall), memory categories, and usage contexts like project filtering. The lack of explanation about side effects (e.g., whether linking overwrites existing memories) or authorization requirements prevents a perfect score.

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 with examples and category tables, making it scannable. However, at over 20 lines it is somewhat lengthy; some example repetition could be trimmed (e.g., the recall-with-query and recall-with-project examples could be combined). Every section earns its place, but the file size could be reduced.

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 the tool has 7 parameters, no output schema, and provides examples covering the main actions, the description is fairly complete for an agent to invoke it correctly. The memory category table and usage examples cover the major operational patterns. However, missing information about return values (especially for recall action) and the absence of edge-case handling (e.g., empty results) slightly reduces completeness.

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 baseline is 3. The description adds significant value beyond the schema by providing memory categories with semantic meanings (task, learning, error, solution, reflection) and real-world usage examples demonstrating parameter combinations. The category descriptions clarify what each value represents, improving over the schema's terse 'Memory category like task, learning, error'.

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 defines the tool's dual purpose: linking memories to agents or recalling agent-specific memories. The verb+resource combination 'Link memories to agents or recall agent-specific memories' is specific and distinguishes it from general memory tools like 'remember' and 'recall' among siblings.

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 includes multiple usage examples demonstrating common patterns (link, recall, search, project-specific recall), which helps an agent understand when to use each action. However, it does not explicitly state when NOT to use this tool (e.g., when to prefer 'remember' or 'recall' tools), lowering the score from 5.

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