draft_linkedin_article

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

Annotations already declare the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false, idempotentHint=false). The description then adds genuinely useful behavior beyond that: billing model ('bills as one content call'), free 24h caching, and crucially that it returns an EVIDENCE PACK plus a composition contract and that YOU write the article (including the methodology box). It doesn't detail the evidence-pack structure, but the added operational context is substantial.

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?

Front-loads the core purpose and word count before routing triggers and mechanics. Efficient overall, though the trailing parenthetical '(Deep trend evidence extraction + multi-section outline + longform article drafting.)' is somewhat redundant with earlier text.

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 complex, multi-stage generation tool with no output schema, the description is nearly complete: it explains the deliverable (evidence pack + contract), the division of labor (agent writes the article), billing, and caching. Minor gaps remain around the exact shape of the returned evidence pack.

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 schema already documents all 7 parameters (including the brand earnings-truth layer, sub_themes rationale, and target_length ±20% contract). The description reinforces the sub-themes and thesis-pressure-test concepts but adds little parameter-level syntax beyond what the schema states, so the baseline of 3 applies.

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+resource (draft a LinkedIn ARTICLE), a concrete scope (800–1,200 words), and the grounding source (Fodda knowledge graphs). It explicitly differentiates from its closest sibling by noting it 'Runs a broader evidence sweep than the post tool,' so an agent can tell it apart from draft_linkedin_post without opening either 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?

Provides explicit trigger phrases ('turn this research into an article…', 'write a LinkedIn article about…') and a use-case condition (long-form thought leadership). The comparison to the post tool gives a clear when-to-use-this-vs-alternative signal.

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