aa_render

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so safety basics are covered. The description adds nothing about what actually gets written, where output lands, or whether it overwrites existing files — the exact behavior an agent needs for a publishing step.

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?

It is a single short sentence with no padding, which is good, but it is under-specified rather than concise — the one sentence spends its words on a cryptic qualifier instead of the operation's mechanics.

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 a write/publish tool with three parameters, no output schema, and two undocumented required arguments, the description leaves too much unknown: input shape, output artifacts, and location. An agent cannot confidently invoke it from this text alone.

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 33%: the emit enum is documented in the schema, but the required `report` and `output` parameters have no description anywhere. The description does not clarify whether `report` is a path, an ID, or an inline model, nor what `output` denotes (destination path? format?).

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 pair ("publish an authored report model") gives a rough idea, but the qualifier "without an investigation workspace" is opaque internal jargon that an agent cannot decode. It does not distinguish this from siblings like aa_finish or aa_validate, which likely also conclude a report workflow.

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 statement of when to call this versus aa_finish, aa_validate, or aa_start, and no prerequisites (e.g. must the report be authored/validated first?). The only hint at a scenario — "without an investigation workspace" — is not explained.

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