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

Annotations already declare the tool readOnly, idempotent, and non-destructive, which lowers the burden on the description. The description adds the useful fact that recorded turns are returned 'in order,' but it does not disclose mode-specific behavior, pagination, or the lossless cursor mechanics. There is no contradiction with the annotations.

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 a single front-loaded sentence with no filler, and every word contributes to the basic purpose. It is concise, though it leans heavily on the title and sacrifices useful mode-level orientation for brevity.

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?

Annotations, a 100%-covered schema, and the presence of an output schema carry much of the burden, so a terse description is acceptable. However, for a 12-parameter tool with four distinct modes, the absence of any high-level explanation of what 'full,' 'selective,' 'progressive,' and 'lossless' mean leaves a real semantic gap.

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 schema already documents all 12 parameters with formats, defaults, and mode-specific meanings. The tool description itself adds no additional parameter-level semantics beyond what the schema provides, so it meets the baseline without exceeding it.

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 uses a specific verb ('Replay') and identifies the resource ('a session's recorded turns') with an ordering constraint, making the core behavior clear. It does not, however, distinguish itself from the similarly named sibling session.recall, so an agent still has to infer which retrieval-style tool is appropriate.

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 provides no when-to-use guidance, no exclusions, and no mention of alternatives such as session.recall or session.continuity. The mode options in the schema imply several distinct use cases, but the description does not help an agent choose among them.

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