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

The description explicitly states 'writes nothing' and 'Public: no sign-in', i.e. a read-only GET, but annotations declare readOnlyHint=false, destructiveHint=true and idempotentHint=false. This is a direct contradiction of the safety profile an agent relies on to decide whether calling is safe.

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?

The body is a single ~250-word run-on paragraph that mixes record semantics, withholding rules, lineage fields, refusal behavior and HTTP routing. It is front-loaded with one clear sentence but the rest does not earn its density; the lineage/field enumeration could be compressed or structured.

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 largely discharges it: it documents content/contentKind, text/system/llmProvider/llmModel/requestTemplate, withheld/note, parent and the lineage fields (wasDerivedFrom, activity, ancestry, wasAttributedTo, generatedAtTime). An agent knows what shape to expect, though the withholding semantics are described only in prose.

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 100% with a single 'id' parameter already documented as 'prompt or artifact id (content hash)'. The description adds provenance context (which store produced the id) but no syntax, format or validation detail beyond the schema, so the baseline 3 applies.

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 opening sentence gives a specific verb+resource+scope: 'Fetch a stored prompt or artifact by id as JSON-LD.' It then distinguishes the two record kinds it returns (an artifact is an LLM reply not stored as a model; a prompt is what was asked) and names the writers (sim_prompt, sim_reroll), so an agent can tell it apart from model-reading siblings like sim_get_model.

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?

Usage is implied rather than stated: the description explains where the ids come from (sim_prompt/sim_reroll) and that a model id or other id kind is refused, naming the tool/route that reads it. That negative routing is useful, but there is no explicit 'use this when you have X instead of Y' comparison against siblings such as sim_get_model.

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