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

Annotations already declare readOnly/idempotent/non-destructive, so the description only needs to add context — and it does: result ordering (freshest first), the cross-channel dedup model, and how to advance pages. It stops short of stating page size, result caps, or whether a full workspace scan is required.

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 the entity definition, then filtering, then pagination — every clause carries information an agent needs and nothing is repeated from the schema.

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 four-parameter filtered list with no output schema and safe-read annotations, the description covers entity identity, ordering, filtering and paging. Page size / truncation behavior is the one remaining gap an agent might need.

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 25%, so the description must carry the load, and it meaningfully explains three of the four parameters: q as name/phone search, scope=personal semantics, and before as the cursor taken from the last row. It leaves the 'client' default value for scope and the length constraints 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?

The description gives a concrete verb+resource ('Clients of the CRM project') and pins down the entity model with 'one person = one card across WhatsApp, Telegram and Instagram', which separates it from conversation- and lead-oriented siblings. It never names an alternative tool explicitly, so the differentiation is descriptive rather than directive.

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?

'Search by name or phone' and 'scope=personal for the owner's personal contacts' spell out the two main usage modes and their selecting conditions. Ordering ('freshest first') and the paging recipe are also stated, but no when-not-to-use condition or sibling alternative is offered.

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