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 well: it discloses the entry shape (time/level/message), the default tail behavior, the non-obvious scan semantics (level/contains scan from the start of the log, not the tail), and a cost warning that output passes through the conversation. It stops short of naming auth requirements or hard truncation limits.

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?

Front-loaded with the core action and efficient overall, though the middle sentence packs several modes together and the CLI recommendation could be tightened. Every sentence still earns its place by covering distinct 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?

For a read-only log tool with no output schema, the description supplies the return-entry format, the filtering/paging model, and a throughput caveat, which is enough for an agent to invoke it correctly and know when it is a bad fit.

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 the baseline is 3, but the description adds real meaning: how level/contains/offset interact with tail and that filtering scans from the log start rather than the tail. It reinforces rather than repeats the schema's parameter docs.

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 ('Read the log of a Scrapy Cloud job'), which cleanly separates it from siblings like scrapy_cloud_get_job_items or scrapy_cloud_get_job_requests. An agent can identify the target artifact (job log) without opening the 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?

Explicitly describes mode selection (tail default, level='ERROR', contains, offset) and routes the agent to an alternative (shub CLI / 'shub log') for anything beyond a small sample. This is actionable when-to-use and when-to-use-something-else guidance.

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