Get run results

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is partly covered; the description nonetheless adds real context by disclosing pagination, the exact row fields returned, and an explicit prompt-injection warning about third-party text. It stops short of stating rate limits or ordering guarantees.

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 tight sentences, purpose first, then row shape, then the safety note — every sentence earns its place. The middle field enumeration is dense but justified because no output schema exists.

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?

Given no output schema, describing the returned row fields is genuinely useful, and the injection caveat covers the open-world risk. However, for a 9-parameter filter tool with zero schema documentation, leaving all filter semantics unexplained is a real gap.

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?

With 9 parameters at 0% schema description coverage, the description must carry the burden, but it only vaguely says 'filter' and lists output fields. The semantics of has_email, categories, min/max_followers, qualified_only, and hide_duplicates are never explained, leaving the agent to guess from names.

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 ('Get a run's discovered accounts') plus the pagination scope, and enumerates the row contents. An agent can distinguish this from get_run_status or get_seen_accounts without opening a schema.

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?

'Filter to narrow the set' gestures at usage but names no alternative tools and gives no when-to-use or when-not-to-use conditions. Nothing tells the agent why it would pick this over get_seen_accounts or when filtering is expected.

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