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

Annotations already cover safety (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context on top: Rial groups return price_toman (Rial / 10), crypto is USD, folder ids derive unit per row from the symbol-name rule, `unit: mixed` adds a per-row unit, unknown symbols stay `as_listed`, and `stale` flags quotes older than 2 days. This is exactly the extra behavioral detail annotations cannot carry.

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 core purpose and field list, then layered with unit/stale semantics and the crypto routing note. Every sentence carries distinct information, though the density of parenthetical asides makes it slightly heavier than it needs to be.

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?

There is no output schema, so the description must describe return values, and it does: price, change, day high/low/open per symbol, plus unit and stale markers. Combined with the category semantics and the crypto-routing caveat, an agent has everything needed to call this 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 description coverage is 100%, so the baseline is 3, and the description earns above baseline by explaining what the category value actually implies: preset groups have known units (Rial/toman vs USD) while a folder id from tj_list_categories resolves unit per row via the symbol-name rule. It does not, however, add anything about limit/offset beyond the schema.

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+resource+scope: a live price table for one TGJU group, listing the exact fields returned (price, change, day high/low/open per symbol). It clearly differentiates itself from siblings by naming tj_get_prices and tj_search_symbols as the right tools for the crypto case.

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?

It gives concrete use cases ('all gold prices', 'all coin prices', 'all currency rates') and an explicit when-not: the crypto preset lists ~27,000 coins in no useful order, so use tj_get_prices for major coins and tj_search_symbols for the rest. Alternatives and the condition selecting them are stated outright.

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

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

Annotations only cover the read/idempotent safety profile, but the description discloses much more: 'time' semantics in Tehran time, that old values mean the market is closed, that `stale: true` marks quotes older than 2 days, that missing symbols fall back to daily close with `source: history`, and that unknown symbols land in `not_found`. That is rich operational context well beyond the annotations.

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?

Opens with what is returned, then layers usage, per-symbol fallback semantics, and the recovery path. Four tight sentences carry no filler and every clause adds call-relevant 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?

There is no output schema, so the description must carry the return contract, and it does: fields returned, timestamp meaning, staleness flag, source alternation, and the missing-symbol list. An agent can invoke and interpret the response without further data.

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 100%, so the baseline is 3; the description goes beyond it by giving example slugs ('price_dollar_rl', 'geram18', 'sekee', 'crypto-bitcoin') and by defining what happens per-symbol when a slug is absent or unknown (daily-close fallback, `not_found`). It does not restate the 30-item cap, minor since the schema declares it.

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 ('Live price, day change, high and low for one or more TGJU symbols') and a clear scope, and 'Use for current rates' implicitly separates it from tj_price_history. It does not name the historical sibling outright, so an agent must infer the boundary rather than read it.

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 a clear situation ('Use for current rates') and routes the agent to tj_search_symbols twice for resolving unknown slugs, which is a real alternative-selection signal. It stops short of an explicit when-not (e.g. 'for past dates use tj_price_history'), so it falls just under full guideline coverage.

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

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely non-derivable behavior: the tree yields folders with ids and symbols that arrive as 'link' items, which tells the agent how to chain calls. It does not mention pagination limits or result ordering beyond what the schema implies.

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?

Three sentences, front-loaded with the resource and the routing advice, then a compact id list. The trailing top-level enumeration is dense but each entry earns its place as a usable parent_id value; it could be moved to a schema enum, but it does not bloat the core message.

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 carries the return-shape burden and does so adequately: it tells the agent the tree contains folder entries with ids and symbol entries with 'link' values. Pagination behavior for very large folders (noted only in the schema's offset text) is the one gap.

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 100%, so baseline would be 3, but the description supplies concrete top-level folder ids (28064 gold, 28066 coin, etc.) that are not in the schema and let the agent call parent_id correctly without a probe. It adds real value over the structured fields.

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 ('Browse TGJU's market tree') and names exactly what is returned (folders with ids, and symbols). That distinguishes it cleanly from siblings like tj_get_prices or tj_category_table, which consume its output rather than produce the tree.

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?

Explicitly routes the agent: call tj_category_table with a folder id for prices, or pass a 'link' symbol to tj_get_prices. It positions itself as the discovery entry point in a named workflow, leaving nothing to inference.

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

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered; the bar is lower. The description adds genuinely new behavioral context by defining unit conventions (*_toman for rial figures, USD for ounce, Brent, Bitcoin and Ethereum), which prevents unit misreads. It does not note data freshness/latency or update cadence, which would matter for a 'today's rates' tool.

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 capability, then the usage rule, then the routing hint — a sensible order with no filler. The long instrument enumeration is slightly list-heavy, though it earns its place by signalling scope.

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 partially compensates by naming the returned instrument groups and clarifying units, which is the key ambiguity for this tool. It stops short of describing the response structure (grouping, ordering, timestamp), which is the remaining gap.

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 tool takes zero parameters, so the baseline is 4. The schema is trivially complete and the description correctly spends no space inventing parameter semantics.

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?

Concrete verb-and-resource framing ('Key Iranian market rates in one call') followed by an explicit enumeration of what is returned: dollar, euro, dirham, gold gram/ounce, coins, silver, Brent, Bitcoin, Ethereum, Tether. It also names the drill-down sibling tj_category_table, so an agent can distinguish it from the other price tools.

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?

'Use first for what are today's rates' is an explicit default-selection rule, and 'Drill into a group with tj_category_table' names the alternative and the condition that routes to it. Nothing about when to pick this over its siblings is left to inference.

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

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

Annotations already cover readOnly/idempotent/openWorld, and the description adds real behavioral detail beyond them: dual Gregorian/Jalali dates, extra `*_toman` fields for Rial symbols, that gap days are simply absent rather than zero-filled, and that `total` counts rows in range for paging. That is exactly the kind of data-shape caveat an agent cannot infer otherwise.

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?

Two short paragraphs, purpose and when-to-use front-loaded, then return-shape and paging caveats. Every sentence carries information; nothing is repeated from the schema.

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 must describe the return payload, and it does: row fields, calendar duality, toman variants, missing-day semantics, and the paging counter. An agent can call and interpret this tool correctly without further reading.

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 every parameter is already documented in the schema. The description's 'page with offset' note adds only marginal context on how `offset`/`limit` relate to `total`; it adds no date-format, default, or boundary detail not already present.

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 — 'Daily history (open, low, high, close, change) of a TGJU symbol' — and even names the row fields returned. The sibling relationship is made clear via 'Use after tj_get_prices', so an agent can separate this historical tool from the current-price tool.

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?

'Use after tj_get_prices' plus 'for charts and trend questions' tells the agent when this tool is the right follow-up. It gives clear positive context but no explicit exclusion (e.g., when to prefer tj_get_prices on its own or tj_market_summary for aggregates).

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

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

Annotations already cover read-only/idempotent/non-destructive. The description adds genuinely new behavioral context: main symbols return a short live symbol while others return a slug, and that slug is answered by tj_get_prices from the latest daily history row with `source: history`. That result-shape disclosure is valuable and not in the annotations or schema.

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?

Three tight sentences, front-loaded with the core action and usage trigger. The final sentence about live symbols vs slugs is slightly dense but earns its place by explaining return semantics absent from any output schema.

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 usefully compensates by explaining what a result contains (short live symbol vs slug) and how slugs resolve downstream. Scope/limit behavior is left to the schema, which fully covers it, so nothing critical 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 description coverage is 100%, so query, scope, and limit are already documented with examples and enum meanings. The description adds no parameter-level detail beyond 'by name' (which maps to query), so the baseline 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 and resource (find TGJU symbols by name) and implicitly distinguishes itself from the price-fetching siblings by positioning itself as the slug-discovery step. An agent can tell immediately this is a search/lookup tool, not a data-retrieval tool.

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 an explicit trigger condition: 'Use when you do not know the symbol slug,' and names the downstream tools to call with the result (tj_get_prices, tj_price_history). It does not state when NOT to use it (e.g., when you already have the slug), but the routing is clear enough to infer.

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