session_peek

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant context: results are 'bounded by retention', it 'makes no model call', and it 'never feeds back into an oracle's context' — the last point materially shapes how an agent should reason about using it.

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?

Front-loaded with the category ('COORDINATION'), then the core action, then use cases, then behavioral caveats. Three sentences with little waste, though the trailing session_list/oracle-context sentence is slightly tangential to invoking this specific tool.

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, but the description compensates by stating what returns ('the complete conversation bounded by retention'), and the retention bound is an important completeness detail. For a 2-parameter read tool with full annotation coverage, nothing essential to correct invocation is missing.

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%, so both parameters are already documented in the schema. The description's 'Optionally scope to one agent_id' merely restates the schema's 'restrict to one agent's turns' without adding format, default, or edge-case detail. Baseline 3 applies when the schema carries the semantics.

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, across instances') and explicitly contrasts its visibility-only nature with the oracle-feeding siblings via the session_list comparison. An agent can distinguish it from session_list, context_read, and trace_get without opening a schema.

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 two concrete use cases ('before joining the work' and 'to recover a finding another instance produced') that tell the agent when this tool is the right pick. It stops short of naming an explicit alternative tool to use instead (e.g. session_list vs context_read) or stating when not to use it, but the context is clear.

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