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

The description discloses side effects such as updating lifecycle status, scheduling follow-up tasks, and recording a submission receipt, and it explicitly denies performing automatic applies/sends/clicks. However, the annotations declare readOnlyHint=true, which directly contradicts the described write behaviors. Per the rubric, a description that contradicts annotations receives a score of 1.

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 dense sentences with the core purpose first, the fallback path second, and the side-effect/non-action caveat last. There is no filler or redundancy; every sentence contributes essential routing and behavioral 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?

The description captures the two input modes, side effects, and non-actions, and the output schema reduces the need to document return values. However, the send and apply booleans are completely undocumented both here and in the schema, and the conditional requirement that queue_item_id is preferred over a set of human-attested fields is only implied rather than explicit. For a 12-parameter tool with zero required parameters, these are meaningful gaps.

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 descriptions already cover 75% of parameters, including title, company, apply_url, submitted_at, queue_item_id, application_id, requisition_id, notes, and actor_id. The description adds helpful mode grouping (queue item vs. human-attested fields) and clarifies that notes are receipt-only, but it does not explain the undocumented send and apply booleans. This is adequate but not especially additive beyond the schema.

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: 'Record that the human manually submitted an application.' It also clearly distinguishes this from automatic application tools by stating it 'never applies, sends, clicks, or submits anything automatically,' which separates it from siblings like talent_scout_compose_application and talent_scout_browser_fill_receipt.

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 gives clear usage context: use this after a human manually submitted an application, prefer a known Talent Scout queue item, and fall back to human-attested details when no live posting exists. It does not explicitly name sibling alternatives or exclusion conditions, but the 'never applies, sends, clicks, or submits anything automatically' boundary provides strong routing guidance.

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