منصة المناقصات — Saudi Government Tenders

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the return contract: counts, open-now tenders, top activities, top winning companies, and page URLs. Since no output schema exists, disclosing the payload is genuinely useful. It does not cover pagination, freshness, or behavior for unknown agency names.

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 sentences, front-loaded with the Arabic definition followed by the English gloss; the enumeration of returned fields is dense and earns its space. The cost is bilingual duplication of the same content, which slightly inflates length without adding 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?

For a one-parameter read-only summary with no output schema, the description supplies what an agent needs to call it and what to expect back. The remaining gaps — no alternative routing and no handling of ambiguous or missing agency names — are minor for this tool's complexity.

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 parameter's meaning ('agency name (Arabic) or id') is already fully documented in the schema. The description restates the same Arabic-name-or-id input without adding format, lookup, or ambiguity-resolution detail, so 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 (summarize) and resource (a Saudi government agency), and enumerates the payload: tender counts, open-now tenders, top activities, top winning companies. A sibling company_summary exists but the description never names it or contrasts the two, so differentiation is inferred from the resource noun rather than stated.

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 is only implied — an agent can infer 'call this to profile an agency', but there is no when-to-use/when-not guidance and no mention of company_summary, market_report, or search_tenders as alternatives. The only explicit instruction is the input form ('by name or id').

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds useful behavioral context by disclosing what the payload contains (including page urls), but says nothing about pagination limits, result caps, or behavior when the company name is ambiguous or not found.

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?

It is two short, front-loaded sentences that lead with the resource and then enumerate returns. The Arabic and English halves are essentially duplicates, which doubles the token cost for monolingual agents, but the parallel phrasing is deliberate and nothing is padded or vague.

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?

For a single-parameter, read-only lookup with no output schema and full annotation coverage, the description carries what is needed: it specifies the identifier and enumerates the returned fields. Only minor gaps remain (no coverage of empty/ambiguous results, no routing to siblings), so it is nearly complete.

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?

There is a single parameter with 100% schema description coverage, so the schema already documents that it accepts an Arabic company name or an id. The description only echoes 'by name or id' without adding format, ambiguity, or fallback guidance, 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?

The description states a specific resource (a company's record in Saudi government tenders) and enumerates the returned dimensions: bids, wins, awarded value, top agencies, activities and recent wins. An agent can distinguish it from agency_summary by the word 'company', though the sibling contrast is never made explicit. It is clear but not fully differentiated in prose.

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 is implied rather than stated: the enumerated outputs imply 'use this to profile a company's tender history', and 'by name or id' hints at the input. There is no explicit when-to-use, no exclusion, and no pointer to alternatives such as agency_summary for government bodies or search_tenders for discovery.

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 readOnlyHint, idempotentHint, non-destructive and openWorld=false, so the safety profile is covered. The description adds genuinely new behavioral information by disclosing the return shape {id, title, text, url, metadata}, which matters because no output schema exists. It stops short of describing error behavior for unknown or malformed ids.

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 compact sentences that front-load the resource and then give the id formats and return shape. The Arabic/English duplication adds length without adding meaning, but nothing is padded or buried.

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?

For a one-parameter, read-only lookup with no output schema, the description supplies everything needed: accepted id forms and the shape of the returned record. Annotations carry the safety profile, so no critical calling information 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 coverage is 100% and there is only one parameter, so the baseline would be 3. The description earns above baseline by enumerating all four accepted id formats (tender:<reference_no>, agency:<id>, company:<id>, report:<YYYY-MM>), whereas the schema documents only the tender example. This meaningfully extends 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 names a specific verb+resource: retrieving the full record for a single id, and enumerates the four id namespaces (tender, agency, company, report). That is far clearer than a bare 'fetch'. However, it does not distinguish itself from close siblings such as get_tender, agency_summary, company_summary and market_report, which appear to cover overlapping ground.

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 statement of when to use this tool versus the many siblings, and no exclusions or prerequisites. The id-namespace list implies the tool is a generic lookup keyed by prefix, but the agent is left to infer that fetch is the general entry point rather than get_tender or agency_summary.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is fully covered. The description adds value by disclosing the shape of the returned record (agency, activity, deadlines, price, winners, links) in lieu of an output 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?

One sentence per language, front-loaded with the core purpose. The bilingual duplication is justified for the Arabic Etimad domain rather than redundant padding, though the enumerations run slightly long.

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 listing the fields the call returns, and the single required parameter is fully documented in the schema. Nothing essential for a correct single-record lookup 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?

There is a single parameter with 100% schema description coverage ('الرقم المرجعي / Etimad reference number'), so the schema already carries the semantics. The description reiterates that lookup is keyed on the reference number but adds no format or validation detail beyond 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 specific verb+resource ('Get one tender by its Etimad reference number') and enumerates the returned fields (agency, activity, deadlines, booklet price, winners, links). The word 'one' implicitly separates it from list/search siblings like search_tenders and open_tenders, though no sibling is named explicitly.

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 is only implied: the presence of a required reference number signals 'use this when you already have an Etimad reference'. There is no explicit when-to-use/when-not guidance and no mention of search_tenders as the alternative for discovery.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds useful domain context (report stage values in_progress/preliminary/final, and the metric families returned), but says nothing about data freshness, latency, or the effect of querying a future/empty month.

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?

Each language version is a single front-loaded sentence with no filler, which is good. But the Arabic and English text convey essentially the same content, so the description is roughly twice the necessary length for an agent consuming it.

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 one required parameter, no output schema, and annotations covering the safety profile, the description carries the burden of describing the return shape — and it does enumerate the report's components (volume, change, agencies, activities, awards, values, stage). Only the stage enum's implications and edge cases for empty months are left unstated.

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 'month' parameter carries both a pattern and a 'YYYY-MM' description, so the schema does the heavy lifting. The description only echoes the month scoping without adding semantics such as timezone, allowed range, or behavior for the current month.

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 deliverable (monthly Saudi tender market report) and enumerates its contents: volume and change, top agencies/activities, awards and values, and stage. This is clearly distinct from entity-scoped siblings like agency_summary and company_summary, though the description never explicitly names those alternatives to sharpen the contrast.

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 is implied by the name and the 'YYYY-MM' scoping — an agent can infer this is the tool for a periodic market-level rollup rather than a per-entity lookup. However, there is no explicit when-to-use, when-not-to-use, or routing guidance versus agency_summary/company_summary/open_tenders.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral fact beyond that: results are sorted by soonest closing. It does not disclose the default page size, the 20-item cap, or pagination behavior.

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 tight parallel sentences (Arabic then English) with the key ordering constraint front-loaded and no filler. The bilingual duplication is functional rather than wasteful, though it doubles the surface length.

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?

For a read-only, no-required-param listing tool with annotations covering safety, the description covers selection and ordering. With no output schema, though, it never indicates what a returned tender record contains or how many results to expect, leaving a modest 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 description coverage is 75%, with region, activity and closing_within_days all documented in-schema and echoed in the description. The undescribed parameter (limit) is also unaddressed in the description, so it adds no meaning beyond the schema; 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 resource and scope: tenders currently open for bidding, with the ordering rule (closing soonest first) and the optional filters named. An agent can distinguish this from get_tender (single tender) or market_report, though no sibling is named explicitly.

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 is implied by 'open for bidding now' and the sort order, which tells the agent this is a list-now tool. However, it never says when to prefer this over search_tenders or search, nor any prerequisite/exclusion, so the routing decision 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 declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: a 20-result cap and the id naming scheme (tender:<reference_no>, agency:<id>, company:<id>, report:<YYYY-MM>) that tells the agent what kinds of entities come back.

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 definition is compact and front-loads the resource scope before the return-shape and query tip. The bilingual duplication (Arabic sentence followed by an English gloss) is slightly repetitive, but each element is short and earns its place.

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 compensates by describing the return format (up to 20 results of {id, title, url}) and id encoding. It stops short of explaining pagination or how to retrieve more than the 20-result cap, which would help for a search tool.

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?

There is a single parameter with 100% schema description coverage, so the schema already defines 'query'. The description adds a real semantic hint beyond it — that Arabic keywords match better — which is actionable guidance the schema does not carry.

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 states a clear verb (search) and enumerates the resources covered: Saudi government tenders from Etimad, agencies, companies, and monthly reports. This implicitly distinguishes it as the broad, cross-entity search versus the narrower sibling search_tenders, though that contrast is never made explicit.

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 is only implied: the multi-entity scope suggests it is the general-purpose search entry point, and 'Arabic keywords match best' hints at query phrasing. There is no explicit when-to-use versus search_tenders/fetch and no exclusions, leaving selection between the two search tools 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/non-destructive, so safety is covered; the description adds genuinely new behavioral detail — a result cap of 20 and that each result carries its platform page URL. No output schema exists, so this return-shape information is valuable, though pagination behavior is still unstated.

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, then filters, then return behavior in two tight sentences. The bilingual duplication doubles the surface length, but each half is efficient and nothing is padding.

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?

For a read-only search tool with no output schema, the description covers what an agent needs: source domain (Etimad), filter scope, result count, and per-result URL. Missing pagination/offset behavior and any note on result ordering or empty-result handling keeps it short of a 5.

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 80%, so the schema already documents query, region, activity and open_only (including the 'Arabic works best' hint). The description maps onto those same filters but adds no syntax or format detail beyond them, and never mentions the 'limit' parameter — 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+resource ('search Saudi government tenders (Etimad) by keyword') and scopes it with filters, so the agent knows exactly what domain is searched. It does not explicitly contrast itself with near siblings like 'search' or 'open_tenders', leaving that differentiation 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?

Gives clear context for use: keyword search with optional activity, region and open-only refinement, making it obvious this is the filtered-discovery tool rather than the single-tender lookup. It stops short of naming when NOT to use it (e.g. fetching one tender by id) or naming the alternative tools.

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