aism_discover

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description's only added behavioral fact is the ordering requirement ("Call first"), which is useful but thin; it says nothing about auth requirements, whether the payload is cached, or how large it is.

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?

One sentence, no padding, and the actionable directive comes last in a natural reading order. It is efficient, though the compressed list of return categories verges on under-specification rather than crispness.

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?

There is no output schema, so the description is the only place to explain the shape of a multi-part discovery payload (scopes/expiry, settings, limits), and it does so only as a bare list. For a "call first" orientation tool, an agent still lacks enough to interpret the response.

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% with a single optional parameter, so the schema fully documents `site` including omit-for-default semantics. The description adds nothing beyond it — "connected site" merely restates the concept, and it does not clarify whether the returned scopes/limits are site-specific.

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?

"Discover the connected site, key scopes/expiry, resources, approved settings and limits" names a resource and enumerates return categories, but the verb is generic and the listed items ("resources", "approved settings") are loose. It does not distinguish itself from the adjacent aism_sites or aism_guide, which likely overlap on site enumeration/introspection.

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?

"Call first" gives an explicit sequencing directive, which is real guidance. However, it does not say what to do with the result, when to skip it (e.g. if already discovered), or how it relates to aism_sites/aism_guide.

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