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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is known; the description still adds real behavioral context that annotations cannot: you get progress while the job builds and full markdown (or a link plus summary for plans) once complete, with results persisted to the Andru account. It stops short of covering timing/polling cadence or what happens when both ids are omitted.

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?

Three sentences, no filler, with the primary trigger front-loaded and the alternative placed last. The first sentence is long and stacked with parentheses and colons, which costs a little readability but not correctness.

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 two-optional-parameter read tool with no output schema, the description covers both input sources and both return shapes well. The one gap is it never says what happens if neither job_id nor asset_id is supplied, which an agent with zero required parameters could plausibly wonder about.

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 100% and the schema descriptions already state that job_id comes from generate_asset/generate_portfolio_brief/get_account_plan and asset_id from list_my_assets, which is essentially what the prose repeats. The only marginal addition is the either/or routing nuance, so the baseline 3 is right.

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?

Names a specific action (collect a finished result for a step) and enumerates exactly which artifacts it returns: an asset from generate_asset, a brief from generate_portfolio_brief, or an account plan from get_account_plan. It also draws the line against the nearest lookalike, list_my_assets, so an agent can pick between them without opening either schema.

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?

Gives an explicit trigger ('use this when the person asks whether something Andru started is done') and an explicit counter-case with the selecting parameter ('To open something already in the library, send its asset_id from list_my_assets instead'). The routing rule between job_id and asset_id is stated, not implied.

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