GameDeal

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses meaningful behavior: prices stay in original currencies while buyer ordering uses EUR conversion, and no purchase or affiliate visit is triggered. That is real added context about side effects and data shape, though the freshness/caching mechanism is only gestured at as 'fresh'.

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 compact sentences, each carrying distinct information (scope, filtering, currency, no-affiliate note), with the core purpose front-loaded. Slightly dense phrasing but 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?

With five parameters at 0% schema coverage and no output schema, the description should do more: exclude_keyshops is unexplained, the shop_type/exclude_keyshops overlap is ambiguous, and what a returned offer entry contains is not described beyond pricing currency.

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 0%, so the description must carry parameter meaning. It does explain slug (must be a confirmed GameDeal slug), platform and shop_type filtering, and limit ordering—but it never mentions exclude_keyshops, its interaction with shop_type, or the enum values, leaving one parameter fully undocumented.

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 fresh, in-stock public offers for a confirmed GameDeal slug.' It also scopes the result set (public, in-stock) so it is distinguishable from get_price_history and search_games, though it never names those siblings 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?

The phrase 'confirmed GameDeal slug' implies a prerequisite lookup step before calling, and 'Open the GameDeal page to choose a shop' sketches the follow-up flow. However, no sibling tool is named and there is no explicit when-not-to-use guidance.

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?

Beyond the readOnly/idempotent annotations, it discloses real behavioral traits: a 90-day and 1,000-observation cap, the aggregation rule (currencies kept separate, platforms/editions/regions merged), explicit coverage and truncation reporting, and the caveat that gaps mean non-continuous data. These are exactly the traits that would cause a wrong conclusion if 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?

Two dense sentences, with the positive capability and its caps front-loaded and the disclaimers trailing. The final clause is a compressed list of three negations that reads tersely but each element 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 does the work of telling the agent what kind of result to expect (discrete observations over a window, not a continuous chart) and that truncation is reported. What it omits is the default window behavior and the exact shape/ordering of returned observations, which an agent would only learn by 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 description coverage is 0%, so the description carries the burden. It partially compensates: it caps 'days' at 90 (matching the schema maximum) and clarifies that 'slug' must be a confirmed public slug. It gives no guidance on the default 30 days, on the meaning of the 1,000-observation cap relative to the window, or on how coverage/truncation are surfaced.

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 (retrieve recorded GameDeal price observations) with hard scope limits (90 days, 1,000 observations, one public slug), and rules out misreadings such as 'market low' or 'availability chart'. It never names its siblings get_game_offers or search_games, so the agent must infer the boundary itself.

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?

'For a confirmed public slug' implies a prerequisite (resolve the slug first, presumably via search_games) and the closing clause implies when-not-to-use this tool (market-low or availability questions). There is no explicit routing statement telling the agent when to pick this over get_game_offers, so usage 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 readOnlyHint and idempotentHint, so safety is covered. The description adds genuinely useful context beyond that: results are 'candidates, not proof of identity' and matching is lexical, which warns the agent about false positives and the need for verification. It still omits return format and the effect of the limit cap, keeping it short of a 5.

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, each doing distinct work: what is searched, how trustworthy results are, and what to verify afterward. The caveat is front-loaded near the top and there is no filler, though the opening and the caveat could be tightened into fewer clauses.

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 should compensate, and it only partially does: it frames results as candidates but never describes what a candidate contains, whether results are ranked, or how limit interacts with ordering. The behavioral warning is valuable, but a zero-coverage 2-param tool with no output schema leaves notable gaps for correct invocation.

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 0%, so the description carries the burden and only partially meets it: it clarifies that the query matches titles, slugs and verified aliases, which is real semantic value for the query parameter. It says nothing about the limit parameter, its default of 5, its maximum of 10, or the 2-120 character bounds on query.

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 public GameDeal titles') and specifies the matching surface (lexical title, slug, verified alias candidates). It is clearly distinguishable from get_game_offers and get_price_history by role, though it never names those siblings explicitly, so differentiation is inferred 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?

The instruction to 'confirm canonical title, product type and slug before comparing offers' implies this is the discovery step preceding offer comparison, which quietly routes the agent toward get_game_offers. However, there is no explicit statement of when to use this tool versus the siblings, nor any exclusion criteria, so usage is only implied.

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