Save Team Rules

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

Annotations already declare the write/destructive/idempotent profile, and the description adds behavior those hints cannot convey: on conflicting saved text it refuses and replaces nothing, and replacement requires explicit consent via replaceExisting. The approval gate on unseen text is exactly the kind of operational constraint an agent cannot infer from the schema.

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 short paragraphs, front-loaded with the action and its purpose, then branching, then consent. Some density is spent re-enumerating the projectId cases already documented in the schema, which is helpful for routing but not strictly additive.

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 an 8-parameter destructive tool with no output schema, the description covers modes, prerequisites, and failure behavior well. The one real omission is the return value: it does not say what comes back on success, and with no output schema the agent has no other source for that.

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 a 3 is the floor, but the description genuinely adds combinatorial guidance the schema only fragments: guidelines = no screen or part, use/never/pairing = part plus kind, brand-wide never = kind never with no part, spec = screen with optional part. It adds nothing about the context or personApproved params beyond what the schema states.

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 concrete verb and resource ('Save the team rules you drafted') plus the downstream effect ('every agent on this account reads them and review checks work against them'). The second paragraph scopes the projectId variant to five specific artifact types, so it is clearly distinguishable from get-team-rules and propose-team-rule among its siblings.

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 prerequisite ('Call get-team-rules first: with no rules saved it gives you the outline and the steps') and an explicit prohibition ('Call this only after the person has read the whole draft and said to save it'). It also spells out the escalation path when the state conflicts: show both, then retry with replaceExisting: true only after agreement.

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