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

Annotations provide only readOnlyHint=true, but the description adds rich behavioral context beyond that: the exact return shape {increases, decreases}, row fields, the fact that marks are fair-value-weighted percent of par, an inclusion threshold, that implausible moves are diverted to `suspect_moves`, and that `coverage` itemizes unread BDCs. This is far more than the annotation conveys.

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?

Dense but front-loaded: the purpose and quoted question come first, followed by return shape, thresholds, and coverage semantics. Every sentence carries operational value, though the prose is long enough that trimming a clause or two would not lose information.

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?

With no output schema, the description fully carries the return contract (increases/decreases rankings, row fields, suspect_moves, coverage, tool_notes caveats) plus the call's caps and data source. An agent has everything needed to invoke and interpret the result.

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 100%, so both parameters are already documented in the schema (including the max 25 tickers, default 10/hard 50 limit, and global-vs-per-BDC ranking). The description largely restates these caps rather than adding new parameter meaning, so the baseline of 3 applies.

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+resource with scope: the largest quarter-over-quarter mark moves across a set of BDC portfolios, and even quotes the user question it answers ('which borrowers got marked up or down the most last quarter, and by whom'). This differentiates it from siblings like ol_bdc_borrower_dispersion, ol_bdc_credit_quality, and ol_bdc_top_borrowers, which cover different facets of BDC credit data.

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 framed question and 'in ONE deterministic call' establish clear usage context, and the eligibility rules (|mark_delta| >= 1.0 point, fair value >= $500k) tell the agent what qualifies. However, it never explicitly names an alternative sibling tool or states when NOT to use it (e.g. vs borrower_dispersion or credit_quality), so exclusions are absent.

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