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

Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is covered. The description adds behavioral nuance beyond that: delivery_presentation returns 'null when it has none', and instruction returns 'the text that run uses' during an open workflow run — useful state-dependent context.

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?

Front-loaded with the core verb/resource before the per-kind bullets, so the essential intent is immediate. The list is long but each bullet justifies itself by documenting a distinct return shape; the project bullet is dense with routing links and markdown resource syntax, which slightly hurts scannability.

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?

With no output schema, the description carries the return-value burden and does so for every kind, including the null case and the run-dependent instruction text. Combined with sibling routing, an agent has everything needed to call it correctly and interpret the result.

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 enum's own description is one line ('Kind of record to read.'), so the description meaningfully extends it by explaining what each of the ten kind values retrieves. It also clarifies the id semantics for delivery_presentation, adding value over the bare schema.

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 ('Get one record by kind and id') and then enumerates every accepted `kind` with the fields each returns. It also names siblings (get_project_state, list_batches, search_works, list_ideas, list_deliveries) so an agent can distinguish this point-lookup from list/search tools.

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 clear routing for follow-up actions ('For next steps call get_project_state; for records use list_batches, search_works...'), which tells the agent when to leave this tool. It does not explicitly state the precondition of already holding an id, but the 'by kind and id' framing and sibling routing make the use context clear.

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