log_change

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

With no annotations, the description carries the full burden. It discloses key behavioral aspects: project lookup priority ('project_id > workspace_path > project_name'), predefined change types, architecture impact levels, and the fact that it maintains 'a complete audit trail.' It does not reveal what happens on duplicate logs, error handling, or whether it returns any response, but for a logging tool the described behavior is sufficiently transparent.

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 longer than average but well-organized with clear headings (WHEN TO USE, CHANGE TYPES, ARCHITECTURE IMPACT, BEST PRACTICES). The opening sentence is direct and impactful. However, the paragraph on 'flexible project lookup' feels slightly tangential to the primary logging purpose and could be tightened, though it remains useful context.

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?

Despite lacking an output schema and annotations, the description is thorough for a logging tool. It covers invocation timing, change classification, project resolution, and best practices for descriptions and related decisions. It does not explain return values, but for an audit-logging operation the agent mainly needs to know how to call it correctly, which is fully covered.

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 description coverage is 100%, so every parameter already has a description. The tool description adds further semantic value by elaborating on the meaning and allowed values for 'change_type' (create, modify, delete, refactor) and architecture_impact (none, minor, significant) and by explaining the precedence of project identifiers. This goes beyond the schema's basic descriptors, helping the agent choose correct parameter values.

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 opens with 'CRITICAL: Log every significant code change for project tracking and history,' which clearly states the tool's verb ('log'), resource ('code change'), and purpose. It also enumerates concrete scenarios (creating files, modifying functionality, deleting features) and distinguishes this logging action from read-only tools like get_recent_changes or update_file_metadata in the sibling list.

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?

Provides explicit usage mandates: 'MANDATORY: Call this AFTER completing any substantial file modification' and a 'WHEN TO USE' section listing exact situations. It also specifies the best practice to log 'after the change is complete and tested.' No alternative tools are referenced, but this is a mandatory audit-logging tool, so the guidance fully covers when and how to invoke it.

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