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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuine behavioral context beyond them - the search is bounded to the last 2000 lines by default and never beyond 5000, and matching is case-insensitive. It does not say what happens with an invalid regex or whether results are ordered, which keeps it short of 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?

Two sentences, front-loaded with the differentiator against the sibling and then the invocation criteria. No filler or repeated schema detail beyond what is needed to convey the bounded-search behavior.

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?

The read path and result shape ('each hit with a few lines around it') are adequately conveyed for a no-output-schema tool, but the required deployment identifier is never mentioned, leaving the agent to infer from the tool name which deployment the search applies to.

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 75%, so the schema already documents lines, context, and pattern; the description largely restates those (2000/5000 window, surrounding lines, case-insensitive). It adds nothing for the required 'id' parameter, which is undocumented in both schema and 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?

States a specific verb and resource ('Find lines in the console log') and immediately distinguishes itself from the sibling deployments.logs by scoping what it covers that the tail view does not. It also names the matching mechanics (word or regex, case-insensitive) so an agent knows exactly what kind of lookup this is.

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 two concrete triggers: when the tail looks fine but something failed earlier, and when hunting the first occurrence of an error. The contrast with deployments.logs is implied by the opening clause, though it never says explicitly 'use deployments_logs for the recent tail' or when not to use this tool.

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