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

Annotations already declare the mutation/not-readOnly profile, but the description goes further by specifying the auth mechanism (Bearer API key), how to obtain one, the failure mode (structured UNAUTHORIZED on anonymous calls), and the 'Not gated' note. It does not spell out whether a removal deletes the building record or just drops it from the candidate list, which is the one remaining behavioral gap.

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?

A single dense paragraph with no filler; the removals/notes grammar is stated compactly. The only structural quibble is that auth boilerplate is front-loaded ahead of the actual action, and the long parenthetical makes it slightly harder to scan than a purpose-first ordering.

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 3-param mutation tool with no output schema, the definition covers auth, action, item structure, id provenance, and gating. It omits return behavior and the effect of a removal on the client-facing review, which an agent could reasonably want before curating.

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 description coverage is 0% at the top level, so the description carries the burden: it documents the item shape of both arrays (removals [{id, reason?}], notes [{id, internal_notes?, client_notes?}]) and — most valuably — names the origin of the required ids (hunt_building ids from realtor_list_candidate_buildings). hunt_id itself and the optional nature of notes/removals are left unstated.

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 concrete verb and resource ('Curate the candidate list') and immediately scopes it with 'WITHOUT sending', which separates it from the sibling realtor_send_to_client. The two sub-operations (removals, notes) make the effect unambiguous.

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 'WITHOUT sending' contrast tells the agent this is the non-send path and the parenthetical points to realtor_list_candidate_buildings as the source of valid ids. It stops short of explicitly naming realtor_send_to_client as the alternative when sending is desired, so the routing is implied rather than stated.

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