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

Annotations declare non-read-only, idempotent, non-destructive, closed-world; the description goes well beyond that by disclosing the immutability model (no in-place edits; retire-then-recreate), the soft-retirement mechanism (active: false rather than deletion), and the provenance link to report_feedback. These are exactly the behavioral facts an agent cannot infer from the hint flags.

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 create/retire capability, then the BrandProfile contrast, then per-mode parameter instructions, then related tools — a sensible ordering with no filler. Slightly dense at four sentences, and the BrandProfile contrast could be tightened, but each sentence carries actionable information.

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 7-parameter, dual-mode mutation tool with an output schema (so return values need no explanation), the description covers what is created, what retirement means, the immutability constraint, and how the optional feedbackId ties in. Nothing an agent needs in order to call it correctly is missing.

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 would be 3, but the description adds conditional semantics the schema does not express: which parameter clusters belong to the create path (phrase + severity, optional feedbackId) versus the retire path (id + active: false). It does not add format or length detail for phrase/reason/channel, leaving that to the schema.

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 pair and resource: 'Creates or retires a content exclusion: a literal phrase Mark enforces (block or warn), optionally limited to one channel.' It also draws an explicit boundary against the BrandProfile concept (prose guidance vs. enforced phrases), so an agent can distinguish it from update_brand_profile and suggest_brand_rules without opening any 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 explicit when/when-not guidance: 'To change an exclusion, retire it and create a new one — exclusions are never edited in place.' It then spells out the two invocation modes ('Pass phrase and severity to create' / 'Pass id and active: false to retire') and names related siblings (get_brand_context, update_brand_profile, report_feedback) for adjacent needs.

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