Teklif

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

Annotations already establish readOnly, non-destructive, closed-world, so the bar is low, yet the description adds real context: no paid or sponsored ranking, a hard result cap of 5, and a card-view return shape. The trailing "Operator-owned Aegis Scanner pricing" is opaque and doesn't clarify 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?

Four short sentences that front-load the verb and the selection modes, with no filler. The final pricing/source note is abrupt and reads as a fragment rather than an integrated caveat.

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?

No output schema exists, but the description covers the return shape (card view), the result cap, sorting, ranking neutrality, and all four parameters' roles. For a read-only comparison tool with zero required parameters this is sufficient to invoke 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 a solid 75%, and the description still adds behavioral meaning: offer_ids overrides category/city, and when omitted the tool returns up to 5 matching offers by default price order. The category enum values (addon, hepsi) remain undefined in both schema and description, and city takes no format guidance here.

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 ("Compares offers") plus the two selection modes: explicit offer IDs sourced from search_offers, or category/city filtering. This implicitly separates it from search_offers, though the boundary (search vs. compare) is never stated outright.

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 trigger ("offers the user has explicitly asked to compare") and describes the fallback path when no IDs are supplied, including the cap of 5 and default sort. It stops short of an explicit exclusion telling the agent to call search_offers first when it has no IDs.

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, openWorldHint=false and destructiveHint=false, so safety is covered; the description still adds real context beyond them by stating it "does not book or purchase" and that links are operator-owned (aegisscanner.com), which addresses trust and side-effect concerns an agent might otherwise hesitate on. It doesn't describe link lifetime or what happens for an unknown/invalid offer ID.

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 short sentences, with the core purpose front-loaded and the safety/ownership caveats following. Every clause carries information — none restates the tool name or 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?

For a one-parameter read-only lookup with no output schema, the description covers purpose, source of the input, return value (a URL), non-mutating behavior, and domain trust. Nothing an agent needs to invoke it correctly 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% with an inline example (aegis-starter, aegis-growth), so the baseline would be 3; the description adds meaning by constraining the ID's provenance to search_offers, telling the agent where a valid value comes from rather than just its type.

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 gives a specific verb+resource pair ("Returns the provider page URL for a single offer ID") and scopes it to a single ID sourced from search_offers, which cleanly separates it from the two siblings (search_offers, compare_offers). An agent can identify the 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?

The phrase "from search_offers" implicitly prescribes the workflow — obtain the ID via search_offers, then call this — and "single offer ID" rules out bulk use. It stops short of naming compare_offers as the alternative for multi-offer evaluation, so the sibling-exclusion is implied rather than stated.

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 the safety profile (readOnly, non-destructive, closed-world), yet the description still adds real value: the default sort order, an explicit "No paid or sponsored ranking" guarantee, and a disclosure of what data currently backs results (operator-owned Aegis Scanner plans). It omits result-count limits and pagination, which would matter for a search 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?

Three front-loaded sentences that move from purpose to filtering/sorting to data scope, with no filler. A few clauses duplicate the schema's enum and default documentation and could be cut.

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 with full schema coverage and no output schema, the definition covers filters, default ordering, ranking neutrality, and current data provenance. Missing only result-size or empty-result behavior, which is minor at this 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 coverage is 100%, so the schema already documents city, budget, sort_by and category including enums and defaults. The description largely restates those ("hepsi = all", "default price, lowest first") and adds no format or edge-case semantics the schema lacks, 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 and resource ("searches offers") plus the filter dimensions and the return shape (cards sorted by sort_by). It never names its siblings compare_offers or get_offer_link, so an agent must infer the boundary, which keeps it from a 5.

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?

"when the user asks for them" gives a minimal trigger condition, and the filter/sort vocabulary is spelled out, but there is no when-not guidance and no routing to compare_offers or get_offer_link. Usage is implied rather than prescribed.

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