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

With no annotations present, the description carries the full burden and does well: it discloses consequences (hidden from lists, counts, exports and outreach) and irreversibility ('No restore, no refund'). It is silent on permissions, partial-failure behavior, and whether the contact still exists as an entity.

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?

Three short clauses, effect first, irreversibility second, gating prerequisite last. No filler; every clause carries decision-relevant 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?

A destructive, non-annotated, no-output-schema tool needs both consequence disclosure (present) and parameter/return clarity (absent). What happens on an invalid or already-deleted id, and what the call returns, are unstated.

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%, so the description must compensate and largely does not. 'One contact' and 'from the search' only weakly imply that id is the person and search_id the search scope; the UUID formats, the relationship between the two, and any constraints remain undocumented.

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 and resource ('Removes one contact from the search') with scoping that implicitly separates it from the bulk sibling sdr_bulk_delete_people. It does not name that alternative explicitly, so the differentiation is inferential rather than stated.

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 an explicit ordering prerequisite: 'Only after sdr_preview_delete_person was approved,' which tells the agent exactly when this tool is legal to call and names the gating sibling. It stops short of saying when not to use it (e.g., multiple contacts -> bulk delete).

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