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

Goes well past the readOnly/idempotent annotations: discloses that no instrument names are returned, that journal text is verbatim investor record rather than assistant opinion, that a verdict contains only conclusion and date, that an unrecognized before_id marker yields an empty page that is not the end of the journal, and what reviews_due_only actually filters on.

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?

Purpose and core behavior are front-loaded, and nearly every sentence carries operational content (pagination, empty-page pitfall, verdict scope, review workflow). It is dense and clause-heavy, though, so the middle section requires careful parsing rather than skimming.

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?

An output schema exists, so return values need not be described, and the description still covers the non-obvious response characteristics (no instrument names, partial verdict content) plus the review workflow and pagination edge cases. Nothing needed to call it correctly is missing.

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 coverage is only 50%, and the description compensates for the two undocumented params: before/before_id resume semantics plus the warning to pair them, and a precise definition of reviews_due_only (review date arrived, no verdict, backing thesis still active on that version). The limit parameter is never mentioned in the description, so semantics there rest solely on the schema's min/max bounds.

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?

States a specific verb and resource ('Read the investor's own decision journal') and enumerates exactly which fields come back (memo, falsifier, conviction, mood, review date, verdict, originating check). It also draws the boundary with get_reflection_history, so an agent can distinguish it from siblings without opening schemas.

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?

Gives concrete trigger conditions ('when the investor asks what they decided or wrote, or when a review is due'), names the alternative for reflection data and instructs 'do not infer relationships from matching dates or text', and states an exclusion ('cannot write a journal or review').

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