add_evaluation

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

With no annotations, the description carries the full burden. It explains parameter roles but does not disclose error behavior (e.g., what happens if identifier doesn't exist), side effects, or any constraints beyond the parameter descriptions. The mention that score has no imposed scale is good, but more transparency about failures would improve the score.

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 concise (6 sentences) and well-structured: it starts with the main purpose, then explains each parameter in a logical order. Every sentence adds value, and there is no redundancy.

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?

Given 4 parameters and the presence of an output schema (which the description need not explain), the description covers the key points. However, it falls short by not mentioning what happens on failure (e.g., invalid identifier) or any return value summary. The missing error handling context leaves a gap for agents.

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?

Since schema description coverage is 0%, the description adds significant value: it explains that text is required, tags enable search, score is a free float with no conventional scale, and identifier must exist. This goes beyond the raw schema and provides meaningful usage context.

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 clearly states the verb 'attach' and the resource 'evaluation to an existing counterparty record'. It distinguishes itself from siblings like 'remember_counterparty' (which creates the record) and 'find_evaluations' (which searches for evaluations), making the purpose specific and unambiguous.

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 provides explicit context: identifier must already exist, and if it's a new counterparty, call remember_counterparty first. It explains the optional parameters (tags for search, score as free float) and notes that using them enables search affordances. While it doesn't explicitly state when NOT to use the tool, the guidelines are clear and practical.

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