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

Annotations are minimal (readOnlyHint=false, no safety profile), so the description carries the burden. It discloses the referral behavior and mandates third-person platform voice, the analyst_id/company auto-resolution, the cost note ('follow-ups cost less'), and the output shape (coverage status, source attribution, referrals). This is substantive behavioral disclosure beyond the empty annotation profile.

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?

Longer than average (five dense sentences with parentheticals), but every sentence carries actionable content — the referral voice rule and company auto-resolution are critical behavioral details. Core purpose is front-loaded in the first sentence. Slightly verbose but justified by density of 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?

With no output schema and no safety annotations, completeness falls entirely on the description. It covers: how to find the right analyst (list_analysts), the full input pattern (analyst_id, company, session_id), the output characteristics (coverage status, attribution, referrals), and how to handle referrals. Nothing an agent needs to invoke 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% with clear per-param descriptions. The description adds meaningful relational context above the schema: the 'brand-cmo'+company pairing, the auto-resolution of 'Nike CMO' to analyst_id+company, and the session continuation semantics with cost implications. This goes beyond baseline 3 by explaining parameter interdependencies.

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 (consult), resource (named Synthetic Analyst expert), and mechanism (expert voice + curated knowledge graph). Explicitly distinguishes itself from 'generic search or standard graph queries' and explains the company-binding special case. An agent can tell exactly what this tool is for.

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 clear context: call list_analysts first to find the right ID, use session_id to continue multi-turn engagements, and omit session_id for one-off questions. Distinguishes from generic search/standard graph queries. Lacks explicit when-NOT-to-use guidance (e.g., when to prefer consult_human_agent or search_graph instead), so it doesn't earn a 5.

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