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

Goes well beyond the readOnly/idempotent annotations: it discloses that the tail beyond listed lines is omitted, that account lines include amounts as well as weights, that funds may be looked through so holding counts are not comparable across modes, and that solved weights represent what a strategy would hold rather than published holdings. These are exactly the caveats that would otherwise cause misinterpretation of results.

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?

Front-loaded with the one-line purpose before the qualifiers, and every paragraph carries distinct information (scope, alternative, caveats). The final caveat paragraph is dense and could be split, but no sentence is redundant.

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 two-parameter read tool with annotations but no output schema, the description does a good job describing the shape of the result and its caveats. What it omits is what happens when neither optional parameter is supplied (both default to null) and what portfolio_id refers to, which an agent needs to call it correctly.

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 never addresses parameters directly: portfolio_id is undocumented in both schema and description, and the holdings alternative is explained only inside the schema. The description adds no syntax, precedence, or defaulting information beyond what structured data already says.

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 concrete resource (what a strategy or account holds) and specifies exactly what is returned: largest lines plus top rows by asset class, asset type, country, sector and industry. It also frames itself as 'a digest, not the full table' and points at open_dashboard for the complete view, which separates it from that sibling; however it never mentions describe_holdings, the closest-looking alternative, leaving some ambiguity.

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 explicit use cases ('is it concentrated', 'how much USA') and an explicit alternative for the fuller view (open_dashboard with tab='weights'). It lacks a stated exclusion against describe_holdings or a note on when a caller should prefer that tool instead.

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