aa_start

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds real value by warning that the call does not analyze the target, so the agent knows the work happens downstream. It does not say where the workspace is created, whether re-invocation overwrites prior state (idempotentHint=false), or how later aa_* calls reference 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?

Two short sentences, front-loaded with the purpose and followed by the scope exclusion; nothing is padded. It is efficient, though the brevity edges into under-specification rather than true density.

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 an 8-parameter, non-idempotent write tool with no output schema and four undocumented parameters, two sentences are not enough. The agent cannot tell what state is created, what the return looks like, or which sibling to call next.

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 only 50% and the description mentions no parameter at all. It never explains target format, what kind=auto infers, when lens/mechanism requires focus, or what output/depth control — leaving roughly half the parameters documented nowhere.

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 verb+resource combination ('Prepare ... investigation workspace') is specific, and the negative clause 'Does not analyze the target' carves out a distinct scope versus the analysis/upsert siblings. What 'target' actually is (repo path, URL, capture) is never stated, which keeps it from a 5.

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?

'catch-up or focused investigation workspace' implies when to use it, but no sibling is named and no sequencing is given, even though the sibling list clearly shows this is the entry point of an aa_* pipeline (aa_inventory, aa_status, aa_finish). The agent must infer that this call precedes them.

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