AWS MCP Server

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

With no annotations provided, the description carries full disclosure burden but fails to state this is read-only, doesn't describe pagination behavior (max_results hints at it but isn't explained), time range limitations, or what execution details are returned (status, duration, errors, logs).

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 single 6-word sentence is efficiently structured and front-loaded. However, extreme brevity leaves gaps given the lack of annotations and output schema; one additional sentence covering behavioral traits would improve utility without sacrificing clarity.

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?

With 100% input schema coverage, the description meets minimum viability for a read-only history query tool. However, given no output schema and no annotations, it should explain AWS Glue-specific constraints (e.g., retention periods, run states returned) to be fully complete.

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% with clear descriptions for all 4 parameters including credential overrides (profile, region) and filtering (max_results). The description adds no parameter guidance beyond the schema, which is acceptable given the schema completeness warrants a baseline 3.

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 uses specific verb 'Get' and resource 'execution history for a Glue job', clearly indicating it retrieves run instances rather than job definitions. However, it could better distinguish from sibling 'aws_glue_get_jobs' (which fetches job configurations) by explicitly mentioning this returns historical run instances/attempts.

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 like 'aws_glue_start_job_run' or general monitoring tools. It omits prerequisites (e.g., job must exist) and doesn't clarify if this shows active runs, completed runs, or both.

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