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.