read_memory

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

The annotations provide readOnlyHint=true, indicating this is a safe read operation. The description adds minimal behavioral context by implying the tool should be used judiciously ('Only if relevant'), but it doesn't disclose additional traits such as what 'memory' entails, potential performance impacts, or how the output is structured. With annotations covering the safety profile, the description adds some value but lacks rich behavioral details like error handling or data format.

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 very brief—two short sentences with no wasted words—making it efficient and front-loaded. However, it under-specifies the tool's purpose and parameters, which leans toward being too terse rather than optimally concise, but it still avoids redundancy and maintains a clear structure.

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 annotations (readOnlyHint) and an output schema (which handles return values), the description doesn't need to cover safety or output details. However, with 0% schema coverage for parameters and no explanation of what 'memory' means in context of sibling tools, the description is incomplete. It provides basic usage guidance but lacks sufficient context for effective tool selection and parameter understanding.

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?

The schema description coverage is 0%, meaning parameters are undocumented in the schema. The description provides no information about the two parameters ('memory_file_name' and 'max_answer_chars'), such as what a memory file is, valid formats, or how max_answer_chars affects the output. This fails to compensate for the schema's lack of descriptions, leaving parameters semantically unclear.

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 'Read memory' is a tautology that merely restates the tool name without adding specificity. It doesn't clarify what type of memory is being read (e.g., files, data structures, or symbolic memory from sibling tools like 'list_memories'), nor does it distinguish this tool from siblings like 'list_memories' or 'find_symbol' that might also involve memory access. The phrase 'Only if relevant to current task' is a usage guideline, not a purpose statement.

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 'Only if relevant to current task,' which provides implied context for when to use the tool—suggesting it should be invoked selectively based on task relevance. However, it lacks explicit guidance on when to choose this tool over alternatives like 'list_memories' (for browsing) or 'find_symbol' (for searching), and it doesn't mention prerequisites or exclusions, leaving gaps in usage clarity.

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