backlog

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

With no annotations provided, the description carries the full burden, disclosing the output format ('JSON array'), the specific filtering logic ('pending or recurring task'), and implied read-only nature. It lacks error condition or performance details, but covers the essential behavioral scope.

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?

Three sentences each earn their place: first establishes purpose and scope, second provides usage context, third specifies the sibling tool alternative. No redundancy or extraneous 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?

For a zero-parameter tool without output schema or annotations, the description is complete: it describes the return value structure, documents the implicit filtering criteria, and integrates with the sibling tool ecosystem by documenting the specific filter syntax needed for task_list.

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?

Input schema contains zero parameters, establishing a baseline of 4. The description appropriately makes no mention of parameters since none exist to document.

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 the specific action ('Return'), resource ('project names'), and scope ('that have at least one pending or recurring task'), clearly distinguishing it from sibling task_list by clarifying this discovers projects while task_list displays tasks.

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?

Explicitly states the temporal workflow ('before filtering with task_list') and provides the exact alternative invocation syntax ('use task_list with filter \'project:name\'') for viewing tasks within a discovered project, leaving no ambiguity on tool selection.

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