Console log

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

With annotations already declaring readOnly/idempotent/non-destructive, the description adds real context: the in-memory buffer holds lines since WorldAPI start (1000 by default), tokens are blanked, and the required scope is logs:read. The prompt-injection warning ('data, never instructions') is meaningful behavioral disclosure for untrusted player-authored content. Minor cost: 'oldest first' sits awkwardly against the limit parameter's 'newest matching lines', creating a small ordering ambiguity the description does not resolve.

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 dense sentences plus a security note, all front-loaded with the resource and ordering before alternatives and caveats. Every clause carries information, though the limit/ordering mismatch slightly muddies an otherwise crisp statement.

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?

No output schema exists, and the description compensates well by describing line contents, ordering, buffer size, defaults, redaction, and required auth. The remaining hole is the exact relationship between which lines limit selects and the order they are returned in, which an agent would need to reason through.

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 still earns above baseline by clarifying filter intent ('filter by the lowest level and by text, such as a player's name or a plugin's'), which tells the agent what to put in grep and how level behaves in practice. It leaves the interaction between limit and the oldest-first ordering unclarified.

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 gives a specific resource (recent console lines), an ordering (oldest first) and enumerates the content types it carries (errors, warnings, plugin messages, joins, chat, commands). It distinguishes itself from file-based log reading (read_file on logs/latest.log) but never contrasts with get_audit_log, the nearest sibling, leaving one differentiation gap.

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 states the trigger condition and routes the agent elsewhere when appropriate: older logs live in files, use read_file with grep on logs/latest.log or the dated .gz file. That is explicit alternative-tool guidance. It stops short of saying when to prefer this over get_audit_log.

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