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

With no annotations, the description carries the full burden and does so richly: it discloses monthly quota capping, that cache hits are free and must not be forced, the PROVIDER_QUOTA_EXCEEDED error with its limit/used/remaining/period_resets_at fields, and the operator-escalation path. Suffix guidance ('report those numbers instead of retrying') is exactly the kind of behavioral context annotations would otherwise provide.

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-loads tier, when, and prerequisites before details, and every sentence adds operational value. It is dense with internal jargon (GC-001, ts_handle, MC-first) that a cold agent may parse slowly, but there is little outright waste.

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?

An output schema exists, so return format need not be explained, and the description still points to result.geocoded_rows for chaining. For a 9-param quota-sensitive tool it is nearly complete, missing only explanations of several hint/session parameters.

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 0% across 9 parameters, so the description must compensate. It explains use_cache, force_regeocode, and accept_suboptimal_geocodes semantics plus the address column mapping for rows, but leaves region_hint, country_hint, map_session_id, min_confidence, and guidance_handle entirely undocumented in both schema and description.

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+resource ('[Tier 1 — Geocode Only]... geocode addresses without full account ingest, or headless bulk geocode') and explicitly distinguishes itself from ingest_accounts. An agent can tell exactly what this tool does and how it differs from the sibling that also geocodes.

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 the user must verify geocode quality first'), when-not ('Prefer ingest_accounts for territory builds'), and prerequisites (none for headless; ts_handle + MC-first when human verifies). Alternative routing is spelled out, not inferred.

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