MCP Server Status

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

Beyond the readOnly/destructive annotations, the description discloses significant behavioral traits: it is slower than normal calls, boots servers from ~/.codex/config.toml, produces no thread/session record in default mode, and starts an ephemeral thread in diagnostics mode. It also explains output interpretation ('unknown' is not a failure, 'degraded' warning semantics, builtIn vs configuredButUnreported). No contradiction with annotations.

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?

Although the description is long, it is exceptionally well-structured with a clear purpose statement, a behavioral caveat section, a two-mode breakdown, and an output interpretation guide. Every sentence adds necessary detail for a tool with no output schema. It is front-loaded with the most important information and uses scannable formatting.

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 the tool's complexity, the lack of an output schema, and the need to explain side effects, timing, and result semantics, the description is remarkably complete. It covers what the tool returns (initialized/unknown/failed), when failures can be detected, how to interpret warnings, and what side effects occur. No gaps remain for a competent agent to use it 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 coverage is 100%, so baseline is 3. The description adds meaningful context beyond the schema for the diagnostics parameter, explaining that it 'starts an ephemeral thread to collect startup notifications' and is the only way to get explicit failure states. It also clarifies the default behavior (inventory only) which ties to the parameter's absence. Timeout and workingDirectory are left to the schema, but the added diagnostics context raises it above baseline.

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 and resource: 'Report what Codex's own app-server says about each MCP server it knows about: auth type, tool inventory, and whether the server initialized.' It clearly distinguishes itself from sibling tools by explicitly stating 'Unlike the other tools, this one deliberately does NOT suppress Codex's MCP servers,' making its unique purpose obvious.

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?

It provides clear when-to-use context and even explains why alternatives would not work ('suppressing them would disable the thing being measured'). It also gives explicit guidance on choosing between default and diagnostics mode, stating diagnostics is 'the only way to get explicit failure states and error text.' This is strong usage guidance with exclusions and mode selection criteria.

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