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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=true, so the mutation and idempotency profile is covered. The description adds valuable context beyond that: whole-list replacement semantics, null-to-clear behavior, the fact that stopLoss is what realized R is measured against, and the OAuth sign-in requirement. It does not contradict the annotations. A small gap is that it doesn't discuss partial-update semantics for fields not mentioned, but the field list and null behavior largely cover it.

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 a single dense paragraph that front-loads the core purpose, then packs the most decision-relevant semantics (replacement vs. additive, null-clearing, what is not touched, return value, auth) into a compact space. Every sentence earns its place; there is no filler or repetition of schema content.

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 14-parameter mutation tool with no output schema, the description covers the key behavioral rules an agent needs: which fields are user-owned, how list replacement works, how to avoid clobbering, null semantics, return value, and auth. It doesn't spell out every parameter's meaning, but the schema covers those at 86%. The main gap is that it doesn't describe error conditions or what happens with invalid keys, but the description is otherwise complete enough for correct invocation.

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 86%, so the schema already documents most parameters. The description adds meaning beyond the schema by explaining the replacement-vs-add/remove distinction, the null-clears convention, and the relationship between stopLoss and realized R. It also points to journal_list_tags for valid tag vocabulary. This is meaningful added value over the schema, though a few parameters (e.g., reviewed, playbookId) are only lightly elaborated in the description.

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 a specific verb and resource ('Annotate a trade') and immediately scopes it to 'user-owned fields only', which distinguishes it from any trade-mutating sibling. It enumerates the exact fields, so an agent knows precisely what this tool does and what it deliberately does not do (fills, prices, P&L).

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 explicit when-to-use guidance: use addTags/removeTags/addMistakes/removeMistakes instead of the whole-list replacement fields when changing a few entries, and check journal_list_tags for existing words. It also states the tool does not touch fills/prices/P&L, which tells the agent not to reach for it for those concerns. This is strong routing guidance relative to siblings.

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