publish_image

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

Annotations flag the write nature (readOnlyHint=false, idempotentHint=false, openWorldHint=true) but say nothing about visibility or timing; the description adds that the post is 'Public and immediate', that confirm=false sends nothing, that a rate cap applies per rolling 24 hours, and that publishing can take up to ~5 minutes. These are exactly the side-effect details an agent cannot infer from the structured fields.

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-loaded with purpose, then the gating condition and the confirm protocol, then per-argument detail — a clean progression with no filler sentences. It is on the long side, but the length is driven by genuinely load-bearing constraints rather than repetition.

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 an open-world, non-idempotent mutation with three params, the description covers preconditions, the safety protocol, parameter bounds, return shape (executed, summary, container_ids, media_id, permalink), rate limits, and latency. An output schema exists but the description's summary of returns and the partial-failure semantics is still additive rather than redundant.

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 0%, so the description carries the full burden and does: image_url is constrained to a publicly downloadable JPEG with 8 MB, 4:5–1.91:1, and 320–1440 px limits; caption has character/hashtag/mention caps; confirm is defined as preview-only (default false) versus publish. None of this appears in 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?

States a specific verb and resource ('Publish a single photo to the user's Instagram feed') with scope qualifiers 'Public and immediate'. The word 'single' distinguishes it from publish_carousel without needing to open 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?

Explicitly restricts use to 'only when the user explicitly asks to post' and prescribes a mandatory two-phase protocol: call with confirm=false, show the preview, then call with confirm=true after approval. It also routes the agent to get_publishing_limit for quota questions, naming the exact sibling.

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