sample_support_pack

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, and the description usefully reinforces this with 'writes nothing and calls no Zeus API', plus discloses refusal behavior for invalid inputs. The enumerated return contents largely restate what the output schema already provides, so the genuinely additive context is the no-write/no-Zeus guarantee and the refusal rules.

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 purpose and safety guarantee, then behavior and rejection rules. The return-content sentence is a long comma list that could be trimmed against the output schema, but overall there is little wasted text.

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 an output schema present and annotations covering the safety profile, the description only needs to add scope, refusals, and the session-id routing note — all of which it does. Minor gaps around whether the paste is written anywhere vs returned remain, but the core is complete.

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 0% for the single 'sample' parameter, so the description must compensate — and it does, naming valid values (beer, travel, yelp), noting a bare-yelp edge case, and stating that sample=api is rejected. This meaningfully exceeds what the bare schema string conveys.

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 operation (produce a read-only Markdown support paste) scoped to three named demo samples (beer, travel, yelp-demo). The verb+resource is clear, though it does not explicitly contrast itself against the many similarly themed siblings (use_sample, recommend_surface), leaving some differentiation to inference.

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 applicability (beer/travel/yelp-demo support requests) and explicit exclusions (sample=api and bare sample=yelp are refused), plus a pointer that session-id-keyed lookups belong in sample_pack_from_turn. It stops short of naming a preferred alternative tool for the refused cases.

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