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

Annotations only tell the agent this is a non-read-only, closed-world write; the description adds what actually moves (prompts, answers, daily figures, content briefs, timeline notes, signals, Gap steps), the collision rule for Gap steps, that other markets' numbers are untouched, that the source project survives but inactive and empty, and that reports/GEO audits go dark unless acceptReportsGoDark is acknowledged. That is substantive behavioral disclosure beyond the structured fields.

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?

Purpose is front-loaded in the first clause and every sentence carries unique information, but the data-migration sentence is a long run-on with a parenthetical that could be split for faster scanning. No filler or repetition.

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 no output schema, the description compensates by describing both the preview response content ('states every count that moves and what stops showing data') and the confirmed result. For a 7-parameter mutation tool, permissions, preview gating, irreversible-looking side effects and the undo path are all covered.

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 the schema already explains each parameter; the description still adds disambiguation the schema does not: which side is the surviving project versus the merged-in one, that omitting a source triggers a listing of mergeable projects, and that acceptReportsGoDark is an explicit user-agreement record. It does not, however, explain the previewToken's interplay beyond the schema text.

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?

The first sentence gives a precise verb, resource and scope: merging another client's AI-visibility project of the same brand into this one as a new market. It names the inverse tool (unmerge_project) and distinguishes the target vs. source project identities, so an agent can distinguish it from add_market or update_project_settings without opening the 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?

It states the prerequisites ('Owners and admins only', 'Requires MCP write actions'), the preview-then-confirm flow, the alternative when no source is supplied ('the result lists the projects that can be merged in'), and the undo path ('unmerge_project undoes the merge'). Usage conditions and exclusions are explicit rather than inferred.

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