unw_banner_plan_add

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

With no annotations, the description does real work: it discloses the write target, the enforced confirmation gate and its no-write failure mode, candidate-based rejection for ambiguous plan names, and a before/after diff read back from Banner on success. It does not cover permissions/auth or what happens if the section is already in the plan (idempotency vs error).

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?

Short, front-loaded, with the most decision-relevant constraint (confirmation is ENFORCED) given its own paragraph. Slight redundancy in the failure-path sentence, which restates the confirmation requirement, but nothing is filler.

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 six-parameter mutation with no annotations and no output schema, this covers the critical ground: write semantics, confirmation gate, ambiguity handling, and the shape of the success response. The gaps are the unexplained `term` parameter and missing permission/idempotency context.

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 0%, so the description must compensate, and it does for most parameters: it defines the crn-vs-subject+number exclusivity, that plan takes an id or exact name, and that confirm must be truthy for a write. `term` is never mentioned, and no value formats (e.g., term code syntax, crn as string vs int) are given, leaving one of six parameters undocumented.

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 and resource ('Add a section (crn) or a course (subject+number) to a Banner plan'), naming both accepted input shapes and the fact that it writes to Banner. It does not explicitly contrast with siblings like unw_banner_plan_create or unw_banner_plan_remove, so the verb alone carries the differentiation.

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 actionable preconditions (confirm must be true, plan must be an id or exact name) and describes the rejection path for ambiguous names, which implicitly tells the agent how to retry. It never says when to choose this over unw_banner_plan_create or unw_banner_plan_remove, so selection guidance is left implied.

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