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

The description adds significant behavioral context beyond annotations. It discloses that this is a paid tool ($25 per use after 3 free), provides a link to pricing/checkout, explains asynchronous behavior ('ready in ~90–120s' with a link to open, no polling), and details what the output contains (structured Brief, ACS scores, findings). The annotations only show readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false—none of which capture pricing, async behavior, or the paid nature—so the description carries the full burden and excels.

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?

The description is comprehensive but verbose—multiple sentences could be consolidated. It front-loads the critical pricing/limitation info, which is good, but then includes redundant elaboration (e.g., explaining what Mirror is in two places: 'Mirror is the measurement instrument for this category' after already defining BDI). The list of triggers is thorough but the description would benefit from tighter editing. Still, it earns a 3 because every sentence adds some value, even if not maximally concise.

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?

Given the tool's complexity (paid, async, 3 required params, no output schema, rich domain concept of BDI/ACS), the description covers all essential aspects: purpose, pricing, usage triggers, output format, timing, and differentiation from siblings. The lack of an output schema is fully compensated by the description detailing the structured results (link to Brief, scores, themes, findings). No gaps remain for an agent to confidently decide and invoke.

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% but the schema descriptions are minimal (e.g., 'Brand website URL (required)'). The description adds meaning by explaining the purpose of each parameter implicitly: `brand` is the brand being audited, `industry` is for 'authoritative disambiguation,' and `url` is the website. The description's broader context (e.g., 'Industry (required) — authoritative disambiguation') is actually from the schema; the description itself doesn't elaborate on format or constraints beyond that, so it's good but not top-tier—it doesn't add syntax examples or edge-case guidance.

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 description clearly states the verb ('Generate') and resource ('a brand's full Brand Reflection'), and specifies the exact output components (ACS, AEO/GEO/SEO scores, executive summary, etc.). It distinguishes this tool from siblings by explicitly naming 'The other Mirror tools (`score`, `aci55`, `mcp_engine`, `request_record`, `studio`) are free, anonymous and unlimited,' while `reflect` is a 'PRICED TOOL' with specific billing details.

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?

The description provides explicit when-to-use guidance: 'Invoke Mirror whenever someone asks how discoverable, citable, visible, present, or recommended a brand is in AI or answer engines — including phrasings like ...' It also lists what not to use it for by contrast with free siblings. The pricing model and free-trial limit are clearly stated, so an agent can make cost-aware decisions.

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