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

Annotations only declare it as a safe, idempotent, non-open-world read; the description adds the operational layer annotations cannot: hard limits (2–52 columns, 100 rows), the 0.25 duration milestone trick, an instruction to infer rather than ask, the presence of an Edit link in the builder, and the critical 'ALWAYS give the user the image link' post-call instruction with the reason inline images cannot be saved.

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 the concrete output description, then selection guidance, then limits, then the link instruction. Dense but every sentence carries information; the image-link sentence is long but justified by its importance.

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 chart generator with no output schema, the description covers what is drawn, hard limits, how to handle missing input, and what to do with the returned artifact. Nothing an agent needs to call it correctly or hand off the result is missing.

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 baseline is 3; the description still adds cross-parameter meaning by tying duration 0.25 to milestone diamonds and tying column counts to the stated limits. It does not walk through the remaining parameters (palette, credit, labelsInBars, width), which the schema already covers well.

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 ('Generate a slide-deck-quality Gantt timeline') and describes the visual output precisely: task bars, milestone diamonds, numbered time columns, section bands. It also names the sibling it is not (process diagram), so an agent can distinguish it from create_process 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?

Gives explicit positive cases ('project plans, roadmaps, launch schedules and anything where WHEN each piece of work happens is the point') and an explicit exclusion routed to an alternative ('use a process diagram instead when only the order of phases matters'). That is the full when/when-not/alternative triad.

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