add_log_source

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

It explicitly reassures that nothing at path is modified, discloses one-time bundle extraction into the server's data folder, and notes that registration persists between sessions. This goes well beyond the sparse annotations and gives an agent a clear safety picture.

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?

The description is front-loaded with the core purpose, then uses short labeled Args and Returns sections to organize details. Every sentence carries needed information, including the important 'nothing modified' guarantee.

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 registration tool with three parameters and nontrivial path handling, the description covers all required inputs, edge-case input types, side effects, and what the call returns. The presence of an output schema means the return-value summary is sufficient.

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?

The input schema contains no descriptions, yet the description fully documents all three parameters: name format, accepted path types with realistic examples, and deployment allowed values. An agent can construct correct arguments without opening anything else.

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 opening line 'Register TPM logs to analyse; remembered between sessions' states a specific action, resource, and persistence behavior. This clearly separates it from siblings like remove_log_source, check_log_sources, and list_log_files.

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 description gives clear, concrete guidance on what inputs are valid: folder, single file, or archive bundle, with examples and a deployment value of 'saas', 'onprem', or 'auto'. It does not explicitly contrast this tool with siblings such as check_log_sources or list_log_files, so it stops short of full when-to-use-versus-alternatives guidance.

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