Read variance report

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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real value: the scope is explicitly limited to one visible view rather than the whole project, and it discloses that there is no undo step and no parameters. It still does not describe pagination, size limits, or empty/missing-variance behavior.

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, front-loaded with the action and return shape, then scope, then the no-parameter/no-undo facts. The middle sentence is dense with two cross-references but each clause earns its place; nothing is wasted.

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?

With an output schema present, return format need not be re-specified, yet the description still summarises the YAML report shape. For a parameterless read tool, scope, dependencies, and mutation risk are all covered, so an agent has everything needed to invoke it correctly.

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 takes zero parameters, and the description explicitly confirms 'It takes no parameters', so there is no ambiguity for the agent. That is the expected baseline-4 handling for a 0-param tool.

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 ('reads the visible variance view') and immediately enumerates the three view variants it can return, plus the per-element contents (planned, actual, variance). An agent can distinguish this from rillsoft_analysis_report_get or rillsoft_project_tree_get without opening a 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?

Clearly conditions usage on the currently visible view and names the two related tools that determine the output: rillsoft_view_state_apply to switch it and rillsoft_baseline_select to choose the baseline. It does not explicitly state when NOT to use this (e.g. for whole-project reporting), so it stops short of a 5.

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