Packages

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds useful behavioral details beyond those: it is a catalog page for context injection, includes every package plus summary, is not a ranked result, and is scoped by knowledgeScope. This gives the agent a clearer behavioral model of what the tool returns and how to treat the output.

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 description is compact and front-loaded with the core purpose. The second and third lines add meaningful guidance about treating the output as a catalog and about knowledgeScope filtering. Slight jargon like 'L0 directory page' costs a little clarity but does not seriously hurt the message.

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 zero-parameter, read-only directory tool with an output schema and rich annotations, the description conveys the essential information: what is returned, how to use it, and what changes when knowledgeScope is set. It could be more explicit about the exact output shape, but the presence of an output schema reduces that burden. Minor ambiguity about where knowledgeScope comes from prevents a 5.

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?

The tool has zero parameters, so the baseline is 4. The description mentions knowledgeScope as a scoping influence, which gives additional semantic context even though it is not a declared schema parameter. There is no param ambiguity to resolve since the input schema is empty.

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 description states this is a directory page listing every package with a summary, which clearly identifies it as a catalog/list operation rather than a search or detail view. It uses resource-specific language (packages, data.packages[].summary) that distinguishes it from sibling tools like info or outline, though it lacks an explicit verb like 'list'.

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?

It gives clear usage context: read the markdown or summaries and choose sources yourself, emphasizing this is a catalog rather than a ranking. It also explains behavior when knowledgeScope is set. It does not explicitly name sibling alternatives or state when not to use it, but the 'not a ranking' guidance and knowledgeScope condition provide meaningful selection cues.

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