start_scoped_audit

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

No annotations are provided, so the description carries the full burden. It does disclose one genuinely useful behavioral guarantee – 'Scope may expand; mutation authority never does' – which is non-obvious and not derivable from the schema. But it omits auth requirements, what state gets created, and the effect of the many mutation_scope_* and mode parameters.

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?

Two short sentences with no waste and the key behavioral caveat front-loaded in the second clause. However, given 16 undocumented parameters and no annotations, the extreme terseness is under-specification rather than effective conciseness.

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 no explanation, but the description is far too thin for a 16-parameter, no-annotation mutation-capable tool. Required parameters (family_id, actor_id, objective) go unexplained and the mode default of READ_ONLY is never mentioned, leaving the agent unable to call it correctly.

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 0% across 16 parameters with cryptic names like mode, audit_kind, max_depth, expansion_relations, and mutation_scope_ids/refs. The description explains none of them, so an agent has no way to know what values mode accepts or what mutation authority entails. This is a severe gap for a 16-param tool.

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 the verb 'Start' and the resource 'SRA/1 bounded recursive audit from a local scope,' which conveys that this begins an audit run. However, 'SRA/1' is undefined jargon and the description does nothing to distinguish it from siblings like audit_context, close_scoped_audit, or record_audit_finding, leaving the agent to infer the boundary.

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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The 'local scope' phrasing hints at context but never states prerequisites or when a sibling like close_scoped_audit or audit_status would be preferred. The agent gets no routing help.

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