get_log

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

With no annotations, the description still makes clear this is a read ('Read the tail'), which is the main safety signal. It adds genuinely useful context about what the file contains, but omits default line count, maximum size, and whether reading has side effects or permission requirements.

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?

One sentence, front-loaded with the action and resource, and the parenthetical is informative rather than filler. Nothing extraneous, though it is arguably too terse given the unannotated parameters.

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 two-parameter read tool the bar is low and there's no output schema to explain, but the missing parameter semantics (default line count, filter behavior) leave real gaps that the description should have closed given zero schema coverage and zero annotations.

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 0%, so the description must carry the parameter burden and it largely doesn't: 'optionally filtered' only gestures at the `contains` parameter without saying it's a substring match, and `lines` is never mentioned at all (no default, no cap). An agent would have to guess both semantics.

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 tail of Cascadeur's log file') and adds what kind of content lands there (errors and Python tracebacks), which tells an agent this is the diagnostic output channel. It doesn't need sibling differentiation because no other tool in the list touches logs, so a 4 rather than 5.

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 parenthetical about errors and tracebacks implies the use case (debugging a failed script or inspecting runtime errors), but the description never states when to reach for this over run_python or get_scene_info, nor any preconditions. Usage is inferable rather than stated.

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