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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotent, but the description adds real behavioral detail beyond them: password and hidden fields are denied, and off-allowlist navigation is denied. It stops short of explaining what happens on denial, whether actions are reversible, or per-action side effects, which keeps it from a 5.

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?

Three compact sentences with the core behavior and the security constraints front-loaded, followed by a documentation pointer. The README URL is useful but the line is somewhat load-bearing in place of inline detail, which slightly weakens the structure.

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 tool with 8 undocumented parameters, no output schema, and destructive/open-world semantics, the description defers heavily to an external README. It never states what read or inspect return, nor what a successful versus denied response looks like, so an agent cannot fully predict behavior from the definition alone.

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 0% across 8 parameters, and the description only echoes the action enum values. It does not explain which parameters each action needs (url for navigate, selector/text for input, attribute for read, timeout_ms bounds), nor the roles of session_id and agent_token, leaving most of the schema uninterpreted.

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?

States a specific verb and resource ('Relay one authorized browser action into the user's already-authenticated browser') and enumerates the seven supported actions. This is clearly distinguishable from siblings like ghostkey_session_create, ghostkey_session_status, and ghostkey_session_revoke, which manage the session rather than perform actions within it.

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 phrase 'one authorized browser action' plus the denial rules implies this is the tool to call once a session exists, but usage is only implied. No sibling is named as an alternative, and there is no explicit when-not guidance (e.g., 'do not call before ghostkey_session_create succeeds').

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