read_log_tail

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so "reads the file without modifying it" largely restates structured data. It adds no detail on behavior the annotations cannot express, such as what happens when the file is shorter than the requested line count or whether large tails are truncated.

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 compact sentences, the core action first and the usage cue second. Nothing is padded and no clause needs rereading.

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?

With rich annotations, a fully documented three-parameter schema and an output schema, the description covers what an agent needs to call it correctly. The only remaining gap is sibling differentiation against read_file and read_file_chunk.

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%, with path, lines (default 200, max 2000) and server_id all documented in the schema. The description only echoes 'last requested lines' and adds no format, encoding, or cost guidance beyond that.

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: return the last N lines from a text log file. The 'tail' framing implicitly separates it from read_file and read_file_chunk, but no sibling is named, so the agent must infer the split.

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?

"Use for recent diagnostics after commands, power actions, or edits" gives a concrete triggering context, which is better than most. It stops short of explicit exclusions — nothing says to prefer read_file_chunk or find_in_file when the interesting output is not at the end of the file.

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