recovery_overview

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

With no annotations, the description carries the behavioral burden and does disclose the important traits: read-only, never automatic replay or auto-retry, no arguments or grants consumed, owner verification required for private archive IDs/commands, and ARCHIVE_ONLY results stay outcome-unknown. The remaining weakness is that several constraints are wrapped in undefined internal vocabulary, so the intent is clear but the precise semantics are not.

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 read-only/no-replay constraint is front-loaded, which is good, but the text then drifts into opaque assertions like 'A production BrokerHost cannot claim this DEV_ONLY aggregation' and 'Not protected Broker acceptance' that cost space without transferring usable meaning. Several sentences would need rewriting, not trimming, to earn their place.

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?

An output schema exists and the parameter set is empty, so the description is not required to explain return values or arguments, and it does cover mode, auth and failure semantics. However, for a tool whose whole point is interpreting recovery evidence, the undefined environment jargon leaves an agent unsure exactly what evidence it will see and how it relates to the sibling session/output tools.

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 and the description confirms 'No arguments', which fully matches the empty input schema. Nothing more is needed on the parameter dimension.

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 gestures at the resource ('current/prior session guidance', a 'DEV_ONLY aggregation') and rules out 'automatic replay', but never states a concrete verb or what the agent actually gets back. Terms like 'BrokerHost', 'DEV_ONLY aggregation' and 'ARCHIVE_ONLY' are used without definition, so an agent cannot crisply separate this from siblings such as previous_sessions or review_status.

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?

It gives one real trigger condition: 'Use after reconnect to interpret current/prior session and opt-in archive evidence in READ_ONLY_MANUAL_RECOVERY mode.' That is genuine when-to-use guidance, but no alternative tool is named and no exclusion says when NOT to call this versus previous_sessions/previous_output, leaving the agent to infer the boundary.

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