context.summarize

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

Annotations only declare readOnlyHint=true; the description goes beyond that by clarifying it stores nothing, calls no external model, and that the actual persistence happens via the caller's own memory.put. That resolves the main ambiguity for a tool named 'summarize' (whether it writes or summarizes server-side).

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?

Three sentences, front-loaded with what is returned, then the write path clarification, then the usage timing. Slightly dense but every sentence carries distinct information with no repetition.

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?

No output schema exists, and the description compensates by enumerating the return payload: the prompt, the summary context, and the last 8 events. The scope of 'last 8 events' (which event stream) is left implicit, which is a minor 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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline of 4 applies. The description adds no misleading parameter claims and correctly implies no arguments are needed.

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 and resource: it returns a prompt asking the caller to summarize the session, plus the summary context and the last 8 events. This is distinguishable from sibling readers like context.read or context.get, which return session data rather than a summarization prompt.

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?

Gives an explicit usage condition — 'at the end of a long session' — and names the follow-up action (memory.put with kind=project_knowledge). It does not explicitly exclude alternatives such as session.checkpoint, but the timing guidance is clear enough to select correctly.

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