Edit a screenshot slide

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description adds genuinely new behaviour: style/device/notification are partial merges that 'change only the fields given', texts land in one locale while other locales keep their own translations, and changes require a separate render step. It leaves one meaningful gap — whether omitting heading/subheading clears them or leaves them untouched.

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?

Very dense for an 11-parameter tool, and the slideId-append behaviour is front-loaded before the field list. The parenthetical field enumeration is crammed and slightly scan-hostile, but nearly every clause carries information an agent would otherwise have to guess.

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 mutation tool with nested objects, 11 parameters and no output schema, the description covers the workflow (read ids, edit, render), partial-update semantics, text limits and localization. The remaining ambiguity about omitted-field behaviour and interaction with theme-level settings is the only real shortfall.

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 73%, and the description compensates with real meaning the schema lacks: the effective 34-character heading cap (40 for caseless scripts) versus the schema's 200 maxLength, the *word* highlight syntax, slideId omission meaning append, and the locale default being the main locale with per-locale translations. Some content merely restates enums, but the added semantics are substantive.

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 — change one slide of the screenshot design, or append a slide when slideId is omitted — and enumerates the editable facets (heading, subheading, plain, layout, style, device, notification). It also distinguishes itself from neighbouring tools by directing reads to get_screenshots and rendering to screenshots_render, so an agent can tell it apart from screenshots_write_headings or screenshots_set_theme.

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 clear operational context: fetch slide ids with get_screenshots first, then render with screenshots_render afterwards, and omit slideId to append a new slide. It stops short of naming exclusionary alternatives such as screenshots_set_theme for theme-wide changes or screenshots_write_headings for bulk heading edits, so an agent must still infer those boundaries.

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