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

With no annotations, the description carries the full burden, and it goes well beyond 'writes a journal note': it mandates using the trader's own words, tells the agent to ask rather than invent content, states that no other trade data can be changed, and explains the refusal and overwrite contract. This is strong behavioral disclosure for safe invocation.

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?

Three focused sentences with the purpose front-loaded and every subsequent clause adding behavioral or decision-relevant information. The length is justified by the refusal/overwrite logic, and there is no filler.

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 5-parameter mutating tool with no output schema and no annotations, the description is remarkably complete: it covers what to write, where, whose words, what to do on conflict, and how to overwrite. Any remaining gaps, such as confirmation response shape, are minor and inferable.

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 schema already documents all five parameters, so the baseline is 3; the description adds meaningful semantics around section (the three fields), content (own words, markdown), and overwrite (only after user approval, otherwise refused). Writing this in natural language genuinely helps an agent decide parameter values, though date/symbol details remain schema-only.

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?

Description opens with a concrete action on a clear resource — 'Record what the trader tells you into their journal' — and enumerates the three distinct sections it supports. It is easy to distinguish from the read/search/list sibling tools, and 'Nothing else about a trade can be changed from here' further scopes the write operation.

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?

It clearly frames the tool's role as capturing the trader's words for one of three journal fields, and the refusal/overwrite flow tells the agent how to behave when content already exists. It does not explicitly say 'use get_journal/search_journal when the user only wants to read,' so read-vs-write routing guidance is implicit rather than explicit.

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