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

With no annotations, the description carries the behavioral burden; the verb 'Read' does signal a non-mutating, safe operation, and the presence of an output schema covers return format. However it discloses nothing about auth requirements, pagination, or limits for the 'turns' payload, leaving gaps that annotations would normally fill.

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 compact sentence with the core action front-loaded and supporting scenarios trailing. It is appropriately sized, though the terse parenthetical reads more like keyword tags than polished prose.

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 single-parameter read tool with an output schema covering return values, the description is nearly complete. Its only shortfall is the thin behavioral/usage context that would matter if annotations were absent and the payload were complex.

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% and the single parameter (session_id) is documented in the schema as coming from memory_session_open. The description adds no further meaning beyond what the schema already provides, so baseline 3 applies.

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?

States a specific verb (Read) and resource (session metadata and turns), which is clear and distinct from siblings in the memory_session_* family (open/append/close/ensure). It does not explicitly name a sibling to disambiguate against, so it stops short of a 5.

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 parenthetical names three concrete use cases (debug, handoff, append failure recovery), giving an agent real context for when to reach for this tool. It offers no exclusions or explicit alternatives, so it stays at 4 rather than 5.

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