aiworkhub_launch_queue_audit_summary_readonly

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

Annotations already declare readOnlyHint=true, so safety is partly pre-covered, yet the description adds genuinely new traits: it reads with plain open(...,'r'), reports log_exists=False without creating the file, and interprets whether all persisted entries are 'blocked_launch_disabled' as the expected steady state. The repeated 'never writes / never launches' clauses and internal module path add bulk but little extra behavior.

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 lead sentence is well front-loaded, but the body repeats the same no-write guarantee three times ('never writes', 'Never mutates queue or audit state', 'FROZEN READ-ONLY CONTRACT') and spends space on internal implementation details (launch_queue_persist.read_persisted_log) that do not help an agent decide or call.

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, so return values need not be spelled out, and the description still characterizes the summary shape and the expected-state flag. Combined with annotations covering read safety and only one optional param, the only missing piece is guidance on choosing this over its sibling readonly 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?

Schema coverage is 0% for the single optional parameter max_entries, so the description carries the burden. It only alludes to it obliquely via 'the last N entries' without explaining the default, bounds, or whether it truncates the summary counts. For one trivially tunable param a baseline 3 is fair, but the gap is real.

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: 'summarize the append-only B119 launch-queue audit JSONL log', and adds the actual output content (counts by decision/to_state plus last N entries). It does not name the closely related siblings (launch_queue_describe_readonly, launch_queue_evaluate_readonly), so the agent must infer the boundary from the word 'audit'.

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?

Usage context is implied rather than stated: the description explains what state is expected ('blocked_launch_disabled' while AIWORKHUB_ALLOW_LAUNCH is unset) which hints at its diagnostic purpose, but never says when to pick this over describe/evaluate or task_audit_log_read. The only routing aid is the shape analogy to aiworkhub_task_audit_log_read, which presupposes the agent knows that tool.

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