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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint=false, so the description is not required to re-state those. The description adds crucial context beyond the annotations: the workspace is shared by all AIsa callers, so results may include records created by other callers. That is exactly the kind of behavioral disclosure that helps an agent interpret results correctly. Minor credit for mentioning 'breadcrumbs' echoing applied filters, though output schema already documents the response shape.

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?

Four short sentences, each adding distinct information: scope, filters/pagination, a workspace-specific warning, and the sibling alternative. No filler or repetition–it earns its length.

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 read-only search tool with 7 optional parameters (all documented in schema), an output schema that defines the response, and a sibling routing hint, the description provides the full context an agent needs: what is searched, what affects the results, and how to invoke the other tool for a different search target. Nothing critical is missing.

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 100%, so the baseline is 3. However, the description claims you can 'filter by name, owner, stage and custom fields,' while the schema shows no 'owner' parameter and no 'custom fields' parameter–labels/stages are the closest but not the same. This inaccuracy can mislead an agent into passing non-existent parameter names. The pagination mention is accurate, but the false extra terms outweigh that benefit.

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 first sentence states a specific action and resource ('Search accounts') and immediately scopes it to 'the companies saved in this Apollo workspace, as opposed to Apollo's global database.' It explicitly differentiates from the sibling `post_apollo_mixed_companies_search`, so an agent can tell them apart at a glance.

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 description names the exact alternative for the other use case ('To search Apollo's global company database instead, use post_apollo_mixed_companies_search') and lists the query capabilities (filter by name, owner, stage, custom fields; paginate with page/per_page). This tells the agent exactly when to pick this tool and when to switch.

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