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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so safety is covered. The description adds genuine behavioral context beyond that: each row's full shape, that the ratio fields are profit ratios used in presumptive assessments, and the explicit caveat that they are not tax rates — a meaningful disambiguation an agent could otherwise misread.

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 opening sentence front-loads purpose and Persian aliases, and the second paragraph is mostly load-bearing field enumeration with one useful caveat. The bilingual term pairs add minor length but are justified by the Persian-language query domain.

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 is the only source of return-value meaning, and it does cover every row field plus the crucial 'ratios are not tax rates' clarification. Complete enough to call correctly; only pagination/limit behavior is left entirely to the schema, which handles it.

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, including the commercial 'no both option' nuance and the year default. The description adds no syntax, format, or defaulting detail beyond the schema, so the baseline 3 for full schema coverage is appropriate.

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 (Find) and resource (tax activity codes) and immediately enumerates what is returned: VAT status, profit ratios, activity type. The Persian aliases (کد فعالیت / اینتاکد) and the named upstream source (tax.gov.ir SearchIntaCode) let an agent distinguish this from tx_goods_search and the other regulation/FAQ siblings without opening any schema.

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 implies the usage context via 'used for presumptive assessments' and the query-example framing, but it never states when to choose this tool over tx_goods_search or when not to use it. There are no explicit alternatives or exclusion conditions, so the routing signal is only implied.

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 description adds real value beyond that: it discloses the return shape (question titles plus page URLs) and the two-step workflow needed to actually read an answer, which the annotations do not convey.

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 sentences, front-loaded with purpose and return shape. The 'Source: tax.gov.ir SearchFAQ' line is marginally redundant provenance but is brief and identifies the backing endpoint; nothing else is wasted.

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 correctly carries the burden of describing returns (titles and URLs) and the follow-up step. Minor gaps remain — no mention of result count limits, pagination, or empty-result behavior — but for a one-parameter lookup tool it is close to sufficient.

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% and the single 'query' parameter already documents its Persian-language expectation, example, and minLength. The description adds nothing about query syntax, language, or matching behavior, 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 (Search) and resource (tax administration's official FAQ), plus what comes back ('matching questions with links'). The 'FAQ' resource distinguishes it implicitly from siblings like tx_regulations_search and tx_goods_search, but the description never names or contrasts those alternatives, so differentiation is left to inference.

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?

There is no explicit when-to-use, when-not, or named alternative. The closing note 'open the url for the answer' does imply this is a first-step index lookup rather than an answer source, which is a useful implicit usage signal, but the agent must infer the routing decision itself.

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 safety (readOnly, idempotent, non-destructive, openWorld), yet the description adds substantial operational context: exact source system, ordering of results (active general IDs first), the meaning of `expired: true`, a 15-30 s first-search cold latency, one-hour caching, and the fact that `total` counts all matches rather than returned rows. This is well beyond what annotations provide.

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, then organized into source/persistence, result ordering, latency/caching, and counting semantics. Every sentence carries distinct, decision-relevant information 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?

There is no output schema, so the description carries the burden of describing return contents (id, description, vat_percent, type, dates, expired flag) and does so fully, along with timing and caching expectations an agent needs before calling.

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 still adds interpretive value by explaining that IDs are 13 digits, that general vs specific and domestic vs imported types exist, and that expired IDs cannot be used, which informs the kind and general_only choices.

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 precise verb and resource ('Find e-invoice goods/service IDs and their VAT rate by description or ID'), including the scope of what is returned. It is clearly distinguishable from siblings like tx_regulations_search or tx_activity_codes without opening their schemas.

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 clear context for when to use it (looking up goods/service IDs by description or 13-digit ID, with kind and general_only narrowing) but never names a when-not condition or an alternative tool. Sibling domains are distinct enough that routing is unambiguous.

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/non-destructive, so the safety profile is covered. The description adds real value beyond that: the upstream source (tax.gov.ir GetAddressGeoLocation), the exact payload shape (booklet block/row, residential/office/commercial and rent values in rial per m²), and the missing-data sentinel string 'عدم وجود اطلاعات'.

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-loads the core purpose in the first sentence, then layers output contents and the geocoding caveat. Dense but each sentence carries information; the Persian term and source citation are justified for disambiguation in a tax-data domain.

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 burden of describing return values (block/row, per-type values, rent values, tax offices, and the no-data sentinel) and states the coordinate prerequisite. Nothing an agent needs to invoke or interpret this tool appears to be 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 the schema already documents latitude/longitude (WGS84, bounds) and the Jalali year with default. The description only restates the coordinate requirement rather than adding format or usage nuance, so the baseline 3 is appropriate.

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 ('Return the official property transaction value per square metre at a map point') and immediately distinguishes itself from the sibling search/regulation tools. An agent can tell this is a point-lookup valuation tool, not a search tool, without opening the schema.

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 prerequisite — the caller must supply coordinates and the server does not geocode — which is exactly the kind of context that prevents a failed call. It stops short of naming alternatives or explicit when-not conditions, but no sibling overlaps meaningfully with this function.

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, so the description correctly spends its budget elsewhere: it names the upstream source, the ordering guarantee, and decodes the status field (معتبر = in force). It stops short of pagination limits or rate limits, but adds real operational context.

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 purpose and scope, then source and item shape in a compact second paragraph. No filler sentences, though the parenthetical script name and source URL are marginally redundant with each other.

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-value burden and does so by enumerating the fields of each result (id, type, title, number, issuer, date, status) and their semantics. An agent can chain into tx_regulation_text without guessing what comes back.

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% and each of the four parameters already carries a description with examples and enum decoding, so the schema does the heavy lifting. The description's note about id/type refers to result fields rather than inputs, adding little parameter meaning beyond the baseline.

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 (search the official tax regulation database), enumerates the covered document kinds (laws, circulars, rulings, opinions), and specifies result ordering (newest first). The mention of passing id+type to tx_regulation_text separates it from that sibling without needing the schema.

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 implies the retrieval workflow by noting that each result's id and type should be passed to tx_regulation_text, which tells the agent this is the discovery step. However, it never states when to prefer it over unmentioned siblings like tx_faq_search or tx_goods_search, so differentiation is only partial.

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/non-destructive, so the description needn't cover safety. It adds genuinely useful behavior beyond annotations: the ~6000-character part size, the parts>1 pagination protocol, and the ability to scope to one article. Return shape (title, kind, number, dates, issuer, PDF link, reading order) is also disclosed.

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 verb+resource sentence, then source, then pagination and article guidance. Three sentences, no filler. Slightly dense but every clause carries actionable 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 compensates by naming the returned fields (title, kind, number, dates, issuer, PDF link, text in reading order) and covering pagination and article scoping. An agent has everything needed to call and re-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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the pagination semantics of `part` (parts count, 6000-char chunks, call again) and the intent of `article` as an alternative to reading an entire ~300-article law, adding practical meaning to both optional parameters.

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 ('Return the full text of one tax law, circular, ruling or opinion, or just one article of it') and implicitly distinguishes itself from the sibling search tool by being a read-one-document operation. The scope (whole document vs single article) is spelled out, so an agent can tell it apart from tx_regulations_search.

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 operational context: source site, the fact that long laws are paginated ('parts > 1 means call again with part=2, 3, ...'), and when to use `article` for large laws. It does not state when NOT to use the tool or name a direct alternative by name (the id dependency on tx_regulations_search appears in the schema, not the description), which keeps it short of a 5.

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