Set project config

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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description adds meaningful behavioral context: writes go specifically to the MCP-managed config and never to legacy project_config.json; only provided fields change; and websiteLocation's default fallback to <project>/site/ is disclosed. This gives the agent safety-critical knowledge about where state is persisted that annotations alone do not convey.

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 three front-loaded sentences: core action first, then key field semantics, then remaining field groups. It is dense (~110 words) but every clause earns its place; the parenthetical list of website tools is slightly long but useful for disambiguation. For a 32-parameter tool this is appropriately sized, not bloated.

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 tool of this complexity (32 params, nested objects, no output schema), the description covers the most consequential cross-field behaviors: partial updates, safe write target, pointer fields with defaults, and the voice-profile feature family. Minor gaps remain — return value/response shape is not mentioned and per-field defaults are only in the schema — but the schema's rich per-property descriptions compensate.

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?

With schema coverage at 78%, the schema already documents most parameters well. The description adds genuine value on top for the least-obvious ones: codeLocation and websiteLocation's pointer semantics (which tool families consume them, the 'leave unset' default), and the voiceLint/etaHints groupings. It wisely avoids re-listing all 32 parameters and instead clarifies cross-cutting behavior.

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+resource ('Update a board's settings') and immediately adds the partial-update semantic ('only provided fields change'). It clearly distinguishes itself from siblings like get_project_config (read), set_global_config (global scope), and set_branding (branding-only) by scoping to a single project's MCP-managed config and naming the field families it configures.

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 conveys clear usage context: it explains that websiteLocation redirects website tools to a shipped site outside the pad (and what happens when left unset), and it warns 'never mutates legacy project_config.json' — an important exclusion. However, it never explicitly says when to prefer this tool over alternatives like set_global_config or set_branding, nor states when not to use it.

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