search_packages

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

With no annotations, the description carries the full burden. It does add behavioral context beyond a bare statement: it discloses that the search spans 'every registry' and that results are returned as one-line summaries — a helpful non-obvious trait. But it omits other behavioral details such as read-only nature, auth requirements, pagination, result limits, or no-match behavior. For a search tool these gaps are moderate, not severe.

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?

Two sentences, front-loaded with the core action, with no filler or repetition. The second sentence about return format is slightly redundant given an output schema exists, but it adds the useful cross-registry scope detail. Appropriately sized for a simple one-parameter tool.

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 low-complexity tool (one parameter, output schema present), the description covers the essential purpose, scope, and result format. Gaps remain: no guidance on when this tool is the right choice versus sibling tools, no query matching details, and with no annotations, the safety profile of the operation is left implied. Adequate but not fully self-sufficient.

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 0%, so the description must compensate for the bare 'query' string property. It partially does by establishing that the query is a package name ('Find packages in the archive by name'), which gives the parameter real meaning. However, it doesn't clarify matching semantics such as exact vs. substring, case sensitivity, or wildcard support, leaving room for misinterpretation.

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 a specific verb and resource ('Find packages in the archive') with a clear method ('by name') and scope ('across every registry'). The purpose is clearly distinguishable from siblings like package_changes, package_versions, and list_projects by name and function, though it does not explicitly name a sibling to disambiguate against.

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 context is implied rather than stated: an agent can infer this tool is for locating packages by name, and the sibling names (package_changes, package_versions, project_report) suggest alternative tools for other intents. However, there is no explicit when-to-use versus alternatives, no exclusions, and no guidance such as 'use package_versions to inspect a known package's versions.'

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