AWS MCP Server

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

Lacks annotations, so description carries full behavioral disclosure burden. Only provides the --readonly constraint, omitting critical execution semantics: whether operation is synchronous/asynchronous, what identifier is returned for tracking, error conditions when job doesn't exist, or immediate cost/resource implications of starting an AWS Glue job.

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?

Extremely terse at two sentences. No wasted words, but potentially too brief for a complex operational tool. Front-loaded with action verb, though operational constraint could be secondary given lack of primary behavioral context.

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?

Insufficient for a 4-parameter mutation operation with no output schema and no annotations. Should disclose return value structure (presumably run ID), async execution model, and side effects (billing, resource consumption). Current description leaves agent underspecified for invocation decisions.

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?

Input schema has 100% description coverage (all four parameters documented). Description adds no semantic clarification beyond schema (e.g., no examples of argument key-value pairs, no clarification on profile precedence). Baseline score applies.

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?

Clear verb ('Start') and resource ('Glue job run') combination. Distinguishes implicitly from sibling tools like aws_glue_get_jobs and aws_glue_get_job_runs by indicating this initiates execution rather than retrieval. However, lacks explicit differentiation from monitoring/listing siblings in the description text.

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?

Provides only a negative constraint ('Blocked in --readonly mode') without positive guidance on when to select this tool versus monitoring alternatives. No mention of prerequisites (e.g., job must exist first) or typical workflow context (e.g., check status with get_job_runs after starting).

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