update_integration

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

While annotations already flag destructiveHint and readOnlyHint, the description adds vital behavioral context: partial updates are honored, changes to key/secret/config are immediately effective and can disrupt live traffic, pricing adjustments modify cost analytics, and related concerns are deliberately isolated. This materially enriches what the bare annotations convey and aligns with them (no contradiction).

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?

Three sentences deliver purpose, side effects, usage safety, and sibling differentiation without any filler. The most important behavioral caveat (disruption risk) is front-loaded, and every clause contributes information an agent needs before invoking the tool.

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 15 parameters, rich schema, and existing output schema, the description covers purpose, mutation semantics, immediate effects, risk profile, and separation from closely related tools. It leaves no major gap: an agent knows what to call, what to expect, and how to avoid unintended consequences. The explicit pointer to get_integration for pre-review further rounds out operational context.

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?

The input schema already covers all 15 parameters with detailed per-field descriptions, so the baseline is a 3 per the rubric. The description adds value by grouping fields into behavioral categories (e.g., 'key, secret mapping, and config' vs. 'pricing adjustments') and clarifying partial update semantics ('Only provided fields change'), which helps the agent understand how parameter combinations behave even though individual properties are schema-documented.

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 opens with a specific verb ('Update') and an explicit resource ('an integration'), then enumerates the exact updatable fields: name, description, API key, provider config, Secret Reference mappings, and pricing adjustments. It further distinguishes this tool from siblings by naming update_integration_models and update_integration_workspaces as separate concerns, making its scope unmistakable.

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 gives concrete guidance: only provided fields change, key/secret/config changes take effect immediately and can disrupt providers or live requests, and pricing multiplier changes affect cost analytics. It also instructs the agent to review get_integration first and explicitly redirects model/workspace access changes to separate tools, providing both usage context and exclusions.

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