Environment

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

Beyond the annotations (destructiveHint, readOnlyHint), the description discloses critical non-obvious behaviors: passwords are never returned ('passwords never returned'), credentials are write-only, delete is explicitly labeled DESTRUCTIVE and requires confirmation, projectUuid auto-resolves from the git repo when omitted, and warm session reuse explains surprising check results. It even explains why a check can report 'no login form' when already authenticated. This is rich behavioral disclosure that annotations alone could not provide.

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 dense but efficiently structured: a one-line action index followed by compact signature-like bullets, then a SESSIONS paragraph that explains a non-obvious cross-tool behavior. Every piece has a purpose, and the most important caveats (destructive delete, password concealment) are front-loaded. It is long because the tool has seven actions, but nothing feels redundant or fluffy.

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 high complexity (7 actions, 16 parameters, no output schema), the description is remarkably complete. It covers every action's inputs, key constraints (confirmation, pagination, auto-resolution, credential management), and the session-reuse context needed to interpret results correctly. It also connects to a sibling tool for an alternative approach. No critical operational detail appears missing for an agent to select and invoke the tool 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?

Input schema coverage is 100%, so the baseline is 3. The description adds meaningful action-level semantics that the flat schema lacks: it groups parameters by action (e.g., 'get {uuid, projectUuid?} → one environment with credentials inline'), clarifies the confirm flag's conditional need, and explains that passwords are write-only and never returned. This goes beyond the schema's per-parameter descriptions, justifying a 4.

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: 'Manage environments (and their login credentials) under a project.' It then enumerates seven distinct actions, making the scope unmistakable and distinguishing it from siblings like project, test_suite, and check_app_in_browser. The action list functions as a precise mini-spec that could not be confused with any other tool.

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 gives clear context for when to use each action and explicitly references a sibling for an alternative behavior: 'pass freshSession:true on a single check_app_in_browser call to bypass reuse without clearing anything.' It also implies when sessions/clearSessions should be used. It does not explicitly state 'use this instead of X' for all siblings, but the action breakdown makes the intended use unambiguous.

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