login_kill

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

With no annotations, the description carries the full behavioral burden and does so well: it names the destructive side effect (the saved login is deleted, forcing a re-prompt), the default no-op on browser cookies, and the flag that widens the blast radius. The 'because those are the user's and they did not ask for them to be removed' clause explains the rationale for the default, which is exactly the kind of context an agent needs before flipping also_browser.

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 sentences, front-loaded with the action and effect, then the trigger, then the important non-obvious default. No filler and no repetition of the name or schema.

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?

Output schema exists so return values need not be described. For a two-parameter destructive tool, the definition covers effect, trigger, default behavior, and the flag's consequence — everything needed to call it safely.

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%, so the description must supply meaning, and it does for also_browser by explaining precisely what true changes. The url parameter is only implied by 'for one site' — no format (full URL vs. domain/host) is given, which leaves a gap on the required parameter.

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 — delete searchts's own saved login scoped to one site — plus the observable consequence ('so the next read of it asks again'). An agent can distinguish this from siblings like login_signin, login_status, and read_url without opening any schema.

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?

Gives an explicit trigger ('Use when a read_url error says the saved login has expired') and an explicit scope exclusion (browser cookies are untouched unless also_browser is true). It stops short of routing the agent to alternatives such as login_signin for re-authenticating or login_status for checking state, so it is strong but not complete on the when/when-not/alternatives axis.

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