GCP MCP

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While it states this is a list operation (implying read-only), it doesn't mention whether this requires specific IAM permissions, whether results are paginated, what format the returned list uses, or any rate limits. For a GCP API tool with zero annotation coverage, this leaves significant behavioral questions unanswered.

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 clear sections (purpose, args, returns) and uses minimal words to convey the essential information. Every sentence serves a purpose: the first states the tool's function, the args section documents parameters, and the returns section describes the output. It could be slightly more concise by combining the purpose and returns statements, but overall it's efficient.

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 this is a read-only list operation with 2 parameters and no output schema, the description provides adequate but minimal coverage. It explains what the tool does and documents parameters, but doesn't address important contextual elements like authentication requirements, pagination behavior, error conditions, or how the returned list is structured. For a GCP API tool with no annotations, more completeness would be helpful.

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 description explicitly documents both parameters (project_id and zone) with brief explanations, which adds value since the schema has 0% description coverage. However, it doesn't provide format details (e.g., GCP project ID format, valid zone patterns) or explain what happens when zone is omitted (returns all zones). With 2 parameters and schema coverage at 0%, the description provides basic but incomplete parameter semantics.

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 clearly states the action ('List Compute Engine instances') and resource ('in a GCP project'), making the purpose immediately understandable. It distinguishes from siblings like 'get_instance_details' (which retrieves details of a specific instance) and 'create_instance' (which creates new instances). However, it doesn't explicitly differentiate from other list tools like 'list_assets' or 'list_gke_clusters', which is why it's not a perfect 5.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over 'get_instance_details' (for specific instance details) or 'list_assets' (which might include instances among other resources). There's no discussion of prerequisites, authentication requirements, or typical use cases for listing instances versus other list operations.

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