session_peek

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

With no annotations, the description carries full responsibility for disclosing behavior. It explicitly states read-only, makes no model call, returns conversation bounded by retention, and never feeds back into an oracle's context.

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 longer than the minimum but every sentence earns its place: coordination context, use cases, optional filtering, read-only behavior, retention bound, and comparison to session_list. It is front-loaded with the core action and not redundant.

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 simple read-only tool with only two parameters and no output schema, the description fully covers what is returned (ordered full turn history), the retention bound, and the absence of side effects. An agent has enough information to call it safely and understand the result.

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 coverage is 100% and the description's mention of 'Optionally scope to one agent_id' mostly restates the schema's own parameter description. It adds no new format, constraint, or semantic detail beyond what the schema already provides.

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: read the full turn history for one session, with scope 'across instances.' It also distinguishes itself from session_list by calling out visibility-only behavior, so an agent can tell them apart.

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 explicit use cases: understand what an agent learned before joining work, or recover a finding another instance produced. It clearly says it is visibility-only and never feeds back into an oracle's context, though it does not explicitly contrast with session_list or context_read.

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