get_market_watch

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

With no annotations, the description discloses key behaviors: it never dumps all rows (always filtered/limited), it comes from a live snapshot, and it returns a structured object {rows, returned, matched, truncated, meta}. It also explains that 'fields' projects specific columns. This provides good transparency into how the tool behaves.

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 concise, using a single paragraph with inline enumeration of options. It is front-loaded with the main purpose and key constraint (always filtered/limited). Every sentence adds value, with no filler or redundancy.

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?

Given the tool has 10 parameters and no output schema, the description adequately covers purpose, filtering options, sort options, return structure, and the live snapshot origin. It leaves a few details implicit (e.g., default sort_by value is 'value' per schema), but overall provides sufficient context for an agent to use the tool 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 0%, but the description compensates by explaining the valid values for sort_by (value, volume, pct_change, last, count), clarifying min_pct/max_pct as percent change, giving codes for flow (1=Bourse, 2=Farabourse, 4=پایه), and describing symbol_contains and fields as column projection. It does not detail all parameters (like descending, limit), but adds significant meaning beyond names.

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 clearly states this tool provides a filtered/sorted view of the whole market from a live snapshot. It uses specific verbs like 'filtered/sorted view' and mentions the Persian term for market watch. It distinguishes itself from siblings like get_index_overview and get_quote by being a broad, filtered market overview.

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 explicitly says the tool is 'ALWAYS filtered and limited' to avoid dumping all rows, implying when to use (for broad overview without overloading). It lists available sort options and filters, giving clear direction on usage. However, it does not explicitly state when not to use it or compare to specific alternatives like search_symbol or run_filter.

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