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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses meaningful behavioral traits: it 'returns ids to pass to fetch,' supports three date formats for locating sessions, is limited to FirmTape's own public pages and finished sessions, and ranks results by keyword. It also clarifies it searches no other site, which adds concrete scope beyond the raw openWorldHint.

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 compact yet dense; every sentence earns its place. It front-loads the core purpose, then covers return behavior, date handling, preferred alternatives, explicit exclusions, and scope limitations in a clear sequence. The non-goal and limits sections are terse but comprehensive, with 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?

With no output schema present, the description compensates by stating that results are ids to pass to fetch. It covers all relevant context for a single-parameter search tool: what content is searched, what a query can be, how dates are handled, when not to use it, and the boundaries of the search space. An agent has enough information to call this tool correctly and route the output to the right next step.

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 describes the single parameter ('A topic, a question, or a trading date'), so the baseline is 3. The description adds real value by giving specific date format examples ('2026-08-24', 'August 24 2026', 'August 2026') and explaining that a date resolves to the corresponding session or sessions. This goes beyond the schema shorthand without being exhaustive.

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: 'Search FirmTape for documents about SPX dealer positioning,' and enumerates exactly what kinds of documents are searched (explainer pages, dated research measurements, finished session archive). It also distinguishes itself from structured-data siblings by noting it returns document ids, making its purpose unambiguous.

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?

Usage guidance is explicit and actionable: it names the preferred alternatives (list_sessions / get_session / get_levels / get_level_history) and the reason (structured numbers vs documents). It also gives clear negative cases: not for documents you already have the id for, and not for any measurement you can name a date for. This leaves no doubt about when to select this tool.

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