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

With no annotations, the description must carry the behavioral load; it does disclose the safety profile ('Read-only'), sort order ('newest first'), and a page-size cap ('up to 200'), which is real value. It says nothing about default page size, whether a total count is returned, or what happens when filters and search_id conflict, so mutation/scope risk is only partly covered.

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-loaded with 'Read-only' and the resource scope, then a dense filter inventory with zero filler. The telegraphic phrasing ('Contacts of a search', 'paging up to 200') borders on elliptical, but every clause carries 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?

For an 8-parameter, unannotated, no-output-schema list tool, the description covers filtering and ordering but never describes what a returned contact contains (relevance score, group, company fields) or that search_id is mandatory. Enough to call it; not enough to predict the response payload.

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 only 13% (just 'source'), and the description compensates well: it enumerates the group enum values, explains source as one hunter's contacts 'incl. pending/phone-only', and names company, role, and min_relevance. It omits that search_id is required and gives no defaults for limit/offset, so compensation is strong but incomplete.

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?

Names a specific verb+resource ('Contacts of a search') and pairs the tool name 'personas' with the concrete term 'contacts', so the agent knows it lists individuals belonging to a search. It stops short of naming the sibling it differs from (e.g., sdr_people_group_counts for aggregates or sdr_export_people_csv for exports), so it is clear but not fully differentiated.

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?

'Read-only' plus the filter list implies this is the way to browse/pick contacts interactively, but there is no explicit when-to-use or when-not-to-use guidance. Nothing tells the agent to prefer sdr_people_group_counts for group totals or sdr_export_people_csv for bulk export, leaving routing to inference.

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