Rebond, offres d'emploi

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds genuinely new behavior: closed/expired/unknown postings return an explicit message, and account data is never exposed. It does not describe payload size or paging, but for a single-record read that is minor.

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, front-loaded with the purpose, followed by error behavior and a privacy scoping note. No filler sentences.

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?

An output schema exists so return-value detail is unnecessary, and annotations cover the safety profile. The description fills in the error cases (closed/expired/unknown) and the data-access boundary, leaving only minor gaps such as what a non-posted error response looks like structurally.

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 0% for the single 'id' parameter, so the description must carry the semantics. It does add value by revealing that the identifier may be a slug as well as a numeric/UUID id — something the bare string pattern does not state — but it gives no length, format, or example guidance.

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 ('Lire le détail public d'une offre Rebond') and the lookup key ('par id ou slug'), so an agent can tell it retrieves a single posting rather than a list. It only implicitly contrasts with the sibling 'search' tool by emphasizing 'détail public ... par id', without naming the sibling.

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: call this when you already have an identifier. There is no explicit when-to-use/when-not guidance and no mention of when to prefer the 'search' sibling instead.

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 and closed-world, so the safety profile is covered. The description adds genuinely new behavior: filters are not auto-relaxed, personal text must be kept out of query, and results must be attributed by citing url. It does not mention pagination or the limit ceiling, which is the only real gap.

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 purpose is front-loaded in the first sentence and every subsequent sentence adds a distinct rule rather than restating. Dense but wasteful only in minor ways, e.g. the standalone sentence about the "comptable à Toulouse" query partly repeats the query-guidance already given.

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 an output schema present the description needn't explain return values, and the citation and fetch routing cover the follow-up workflow. The only omission relative to a 5-parameter search tool is any hint about result volume or the limit parameter, which an agent may need for narrow queries.

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 0%, so the description must carry parameter meaning, and it does explain query, city, contract and remote plus the privacy rule for query text. However, limit (default 5, max 20) is never mentioned and no value formats are given for city or the enum, so compensation is only partial.

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?

"Chercher des offres publiques Rebond" states a specific verb and resource, and the closing sentence routes detail lookups to the sibling tool fetch, so an agent can tell the two apart without opening either 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?

Explicitly splits the input strategy: query carries the job title/keywords, while city, contract and remote handle structured criteria, with a concrete combined example ("comptable à Toulouse"). It also names the alternative path (fetch with an id for detail) and warns that filters are not widened automatically, which prevents an agent from assuming fuzzy fallback.

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