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

With no annotations, the description carries the full load and does well: it discloses determinism ("no LLM"), that no house rates or milestone conventions are hardcoded, that all team checks default off, the 50-story batch cap, and that "missing fields ARE findings." The remaining gap is return-value shape — no output schema exists and the description never says what a finding looks like.

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 purpose and sibling disambiguation, then the optional-config switch, then limits. The long parenthetical enumeration of team-specific checks is dense but each item maps to a real config field, so it earns its space; it could be split into shorter sentences for scannability.

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 3-parameter tool with heavy nesting and no output schema, the description covers modes, limits, and scoping well. The one missing piece is the shape of the lint findings, which an agent would need to interpret results since no output schema documents it.

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 baseline is 3, but the description adds real semantic value: it explains that rate_config is optional and that omitting it disables all team-specific checks, and it names the five check families the nested config unlocks. It adds the cross-batch evaluation rule for dependencies and companion types.

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 ("deterministic structural quality linter for user stories") and enumerates the exact concepts checked (narrative completeness, acceptance criteria, dependency IDs, CRUD split, pagination). It explicitly positions itself relative to the sibling ticket_lint, so an agent can distinguish the two 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?

Clearly signals two modes: omit rate_config and only universal checks run, or supply it for team-specific checks. It also states batch max of 50 and that dependency/companion checks are cross-batch. It does not address overlap with other quality siblings like acceptance_criteria_validator or dependency_check, leaving the routing decision partly implicit.

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