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

Beyond annotations (destructiveHint=true, readOnlyHint=false), it discloses meaningful behavior: add is a no-op for an existing publisher, remove is blocked for contacted/won/tracked publishers, brand's own site can't be added, editor access is required, and saved publishers surface on the Outreach page. This is rich behavioral context that annotations alone don't provide.

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 one-line summary is front-loaded, followed by compact mode bullets and a clean Args list. Every sentence adds operational information—no filler, and the length is justified by three distinct actions plus auth/validation caveats.

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 covers list output (publisher, status, saved idea), side effects on the Outreach page, permissions, and validation guards. There is no output schema, yet the return behavior for add/remove is not described (e.g., confirmation or resulting board state), which leaves a small but 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?

Schema coverage is only 13%, so the description carries the parameter burden: it explains each functional argument, marks domain as required for add/remove, ties research_id to discover_publishers, and gives character limits for article_idea, rationale, and proposed_route. Only user_intent is omitted from the Args block, but the schema already describes it as an analytics hint, so the practical parameter semantics are fully covered.

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?

Opens with 'Read or change the brand's outreach publisher shortlist,' a specific verb + resource, then enumerates list/add/remove modes. The name and description identify the domain object (publisher shortlist) clearly, and this is distinct from sibling tools like discover_publishers and manage_tracked_article.

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 gives explicit when-to-use constraints: from discover_publishers pass research_id, domain required for add/remove, already-contacted/won/tracked publishers can't be removed, and editor access is required for mutations. It doesn't explicitly name an alternative tool for publisher management or say when not to use this tool, but the mode-based instructions and exclusions provide clear practical guidance.

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