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

The description goes well beyond the annotations: it reveals the monthly quota exemption, anti-abuse bound, Free plan watermark behavior, the finalCaption output the agent can rely on, story-caption ignoring, and safe timeout/idempotency semantics. These are meaningful behavioral details not implied by readOnlyHint, openWorldHint, or destructiveHint alone.

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 description is dense but front-loaded with the core action and then layers plan/caption/timeout semantics. Every sentence contributes useful operating information, though some details slightly overlap with the schema, such as the idempotency guidance. It is longer than minimal but appropriate for a mutating tool with multiple modes.

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 the tool's complexity (9 parameters, no output schema, multiple post types), the description covers all decision-critical behavior: connected-account prerequisite, immediate publication, plan-specific caption watermarks, story caption behavior, carousel slide counts, and safe retry semantics. An agent has what it needs to invoke this tool correctly and avoid duplicate posts.

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 100%, so the baseline is 3. The description adds practical semantics beyond the schema: the idempotency_key retry flow with draft_id, the fact that stories ignore captions, and that finalCaption reflects what was actually posted. These additions help the agent choose and sequence the parameters correctly.

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 names a specific verb and resource: publish the user's own images and caption to their connected Instagram account, and clearly differentiates the three content forms (story, feed, carousel). It also distinguishes itself from sibling tools by emphasizing bring-your-own-content and immediate publishing. This makes the purpose unmistakable even alongside publish_draft.

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 clearly states key usage conditions: it requires a connected account, publishes immediately, and does not support scheduling. It also positions this as the free, non-quota-consuming publishing surface organically, though it does not explicitly name publish_draft or other alternatives as the recommended alternative.

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