add_target

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

Annotations are absent, so the description carries the full burden, and it delivers richly: targets are never built, never listed by list_ready, map to a GitHub issue whose sub-issues are tasks, forbid build fields, and their deps 'sort its work below rows that are clear' while priority 'multiplies the rank of everything it holds.' This goes well beyond a bare mutation disclosure.

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?

Front-loaded with the definition, then constraints, then parameter behavior; every sentence earns its place and there is no boilerplate. It is long, but the conceptual complexity (target vs. task, altitude, derived progress) justifies the length rather than padding it.

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 10-parameter, semantically unusual tool with no annotations, the description covers the concept, exclusions, required fields, the 'why' criterion, and dependency ranking. It omits edge behavior (deps cycles, what happens if a build field is passed anyway) and doesn't route to roadmap/list_planning siblings, but with a 100%-coverage schema and an output schema present, these are minor gaps.

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%, so the baseline is 3. The description adds some nuance — deps 'rank every task underneath' and the WHY-test for brief ('If you cannot write the why, it is not a target yet') — but much parameter meaning (priority multiplier, tags replace behavior, project default, brief definition) already lives in the schema, so the net addition beyond structured fields is thin.

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?

Opens with a specific verb+resource — 'Create a roadmap TARGET' — and immediately distinguishes it from siblings: 'A target is never offered by list_ready and is NEVER BUILT,' with progress 'derived from the tasks that name it (add_task/edit_task `target`).' An agent can tell add_target apart from add_task and list_ready without opening either schema.

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?

Gives an explicit when-not and route: 'If you cannot write the why, it is not a target yet; file it as a task, or leave it unfiled,' and references the sibling add_task by name. It also states hard exclusions (cannot carry build fields, cannot serve another target). However, it never states a positive 'use this when...' instruction or compares against roadmap/list_planning siblings, so positive routing is left mostly to inference.

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