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

Annotations already cover safety (readOnly, non-destructive, closed-world), so the description's job is thinner. It still adds genuinely useful behavior: ordering ('newest last') and a content limitation ('summaries only'), naming the exact summary fields returned. It doesn't mention pagination or result caps, which is the remaining gap for a list tool with no output schema.

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 tight sentences; the scope and ordering come first, then the return-shape caveat, then the sibling redirect. Every clause carries information an agent needs.

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 single optional parameter, read-only list tool, this covers scope, ordering, and return granularity plus the sibling route. The one missing piece is volume behavior (pagination/result limits) on a tool with no output schema, which would matter if projects hold many widgets.

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% and the 'project' parameter already documents that it runs the call in a different project. The description adds only the 'current project' default framing, which is already implied by the schema. Baseline 3 is appropriate.

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 verb+resource (list every widget), scopes it to the current project, and distinguishes itself from the read_widget sibling by contrast. An agent can immediately tell this is a summary enumeration rather than a detail fetch.

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?

Explicit routing: use this for the collection, use read_widget for a single widget's full content. That names the alternative and the condition that selects it, leaving nothing to inference.

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