maket_gmail

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

With no annotations, the description fully discloses behavior: OAuth dependency, result caps (50 messages, 3000-char body truncation), side effects (asset library ingestion for images, raw drop for others), and that drafts are never sent. It could mention error handling or rate limits but covers the critical aspects.

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 well-structured with a lead-in sentence and a bullet list of actions. It front-loads critical guidance (connect first). Some redundancy exists (e.g., 'Requires with_read=true at connect time' repeated thrice), but every sentence adds information without fluff.

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 17 parameters, no output schema, and no annotations, the description covers tool usage comprehensively. It explains each action's inputs, prerequisites, and results. It could specify return formats or error states, but for the complexity, it provides sufficient context for an agent to use the tool correctly.

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 adds value by grouping parameters per action (e.g., draft parameters with fallback logic, connect's with_read toggle, search's query syntax). It explains parameter interactions beyond the schema, such as when fields like 'category' apply only to image attachments.

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 explicitly states the tool's purpose: 'connect Gmail, search/read mail, download an attachment, or create a draft from a Maket document.' It enumerates five distinct actions with specific verbs and resources, distinguishing it from sibling tools (none of which mention Gmail).

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 starts with 'When to use:' and clearly states the prerequisite: 'All actions except connect require an active OAuth session — call connect first.' It provides action-specific requirements (e.g., with_read=true for search/read). However, it lacks explicit when-not-to-use or alternatives, though sibling tools don't overlap.

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