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

With no annotations, the description carries full behavioral disclosure. It covers authentication requirements, job ownership, status lifecycle, progress fields, truncation behavior, and the sync alternative, going far beyond the schema.

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?

The structure is organized into purpose, input, output, and usage note. The keyword blocks at the top are redundant and add noise, but the rest is efficient and information-dense without being bloated.

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?

There is no output schema, so the description must explain return values; it does so thoroughly with statuses, the progress object shape, and the summary aggregates. Nothing essential for correct invocation seems 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?

Although schema coverage is 100%, the description adds meaningful parameter meaning: jobId is defined as the id returned by screen_companies, and includeItems is explained with its default value, item limit, sorting rule, and truncation signal.

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 opens with a specific verb and resource: 'Ia starea și rezultatul unui job de verificare portofoliu creat cu screen_companies.' It is clearly distinguished from the sibling screen_companies by framing get_screening as the polling/result tool for asynchronous jobs.

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?

It explicitly states when to use it: after an async call for more than 20 companies, and when not to use it: for ≤20 companies screen_companies already returns the full report synchronously. This gives the agent actionable routing between siblings.

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