review_agentcore

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses that execution is local against `terraform show -json` output, that nothing is transmitted and no AWS credentials are needed, and what each finding contains (severity, pillar, resource address, Terraform fix, source doc). It does not cover failure behavior for an unreadable plan path, the size/volume of findings returned, or how accepted `skips` alter the report.

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 core purpose and the local/no-credentials guarantee are front-loaded before the rule inventory, and the trigger examples are pushed to the end where they belong. The rule enumeration is a long comma-separated list that borders on density for density's sake, but each clause names a distinct check an agent could otherwise not infer.

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 fairly complex tool with no annotations and no output schema, the description covers inputs (plan, optional bill and tag), scope of analysis, and the shape of returned findings. The remaining gap is the `skips` workflow — how a user suppresses a known-acceptable finding and how that surfaces in the report — which an agent would need in order to use that parameter correctly.

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 description coverage is 100%, so the schema already documents all four parameters, and the description largely restates them ('FOCUS bill', 'a tag such as agent=genie'). It adds the useful implication that the tag scopes bill lines to this agent and that bill_path is optional enrichment rather than required input, but the `skips` parameter and its skip-a-finding semantics are never mentioned in the description.

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 states a specific verb and resource — a Well-Architected review of an Amazon Bedrock AgentCore deployment — and then enumerates exactly what is inspected (Runtimes, Harnesses, Gateways plus surrounding IAM, logs and alarms). It distinguishes itself from cost-only siblings like analyze_bill or estimate_agent_cost by framing cost as an add-on to a rules-based review, and the quoted trigger phrases make the boundary explicit.

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 'Use for:' list gives concrete user phrasings ('is this agent production-ready', 'what does this agent cost and what should we fix') that map cleanly to invocation. The cost clause also implies a conditional — cost analysis only happens when a FOCUS bill is supplied — but no sibling tool is named as an alternative for cost-only or non-AgentCore questions, and there is no explicit 'do not use for' statement.

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