The Deploy Log

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 behavioral context beyond that: rows are identical to the week page, and each row carries the publisher's own source URL. It stops short of describing result size, ordering, or what an empty week returns.

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 short sentences with no padding, and the scope-defining clause is front-loaded. The second sentence on source URLs is marginally supplementary but still earns its place by telling the agent what each row contains.

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 tool with complete schema coverage, full safety annotations, and no output schema, the description is nearly sufficient. It states the data source and the per-row payload, with only result ordering and empty-result behavior left unspecified.

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%: the single 'week' parameter is typed as a string with pattern ^\d{4}-W\d{2}$ and an example (2026-W39). The description adds no further syntax, format edge cases (e.g. out-of-range weeks), or invalid-input behavior, 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 names the specific resource (every row of The Deploy Log) and scope (one ISO week), so an agent knows it returns a week-bounded slice rather than a search or a recent feed. It does not explicitly contrast itself with siblings recent_deployments or search_deployments, so the differentiation is inferred from the 'one ISO week' scoping 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?

There is no explicit when-to-use guidance and no mention of the sibling tools as alternatives, despite the near-identical recent_deployments and search_deployments sitting next to it. The phrase 'the same rows as its week page' hints at parity with a UI view but gives the agent no rule for choosing this tool over its siblings.

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 and destructiveHint=false, so the safety profile is covered structurally. The description adds genuinely useful behavior beyond that: results are sorted newest-first, and each row carries what shipped, when, and the publisher's own source URL, which tells the agent what the return payload looks like without 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?

Two short sentences, zero filler, with the core identity and ordering front-loaded before the optional filter and row-shape details. Every clause 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 compensates by describing the returned row contents, and read-only annotations cover the mutation question. It stops short of mentioning the limit default of 10 or maximum of 25, but those live in the schema, so nothing essential 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 description coverage is 100%, so lane, limit and company are already fully documented, which sets the baseline at 3. The phrase 'optionally one lane or one company' adds a small semantic nuance (these filters are typically applied singly), but it does not clarify defaults or combinability beyond what the schema already states.

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 concrete resource (the newest rows in The Deploy Log) and an explicit ordering (newest first), so an agent knows it returns a reverse-chronological feed rather than a search result. It does not name its siblings (deployments_in_week, search_deployments), so the distinction is implied by 'newest' 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?

'Optionally one lane or one company' implies how to narrow the feed, which is a usable usage hint. However, there is no explicit when-to-use guidance and no mention of when to prefer search_deployments or deployments_in_week over this tool, leaving routing 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 a safe, idempotent, closed-world read, so the safety bar is met structurally. The description adds real behavioral context beyond that: results are ordered newest-first, matching is restricted to company/subject/what-shipped fields, and each row exposes the publisher's source URL. It stops short of stating limits or result-count behavior, but the additions are substantive.

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 sentences, no filler, with the resource and ordering constraint front-loaded and the return-content note last. Every clause 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 only two parameters, full schema coverage, and annotations covering safety, the description supplies the remaining essentials: match scope, ordering, and that rows include a source URL (useful given no output schema). It could note result-count/pagination behavior but no critical gap remains.

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 baseline is 3. The description goes beyond the schema by naming which fields the query term is matched against (company, subject, what shipped), which the schema's generic 'Words to find' text does not convey. It does not elaborate on limit, which the schema handles.

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: returning rows of 'The Deploy Log' whose text fields match a query. The keyword-match framing implicitly separates it from the recency-oriented siblings (deployments_in_week, recent_deployments), but it never names them, so the 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?

Usage is implied: this is the free-text search tool, so an agent can guess it is for keyword lookups rather than time-window listings. However, there is no explicit 'use this when... use X instead when...' routing against the two sibling tools, leaving the choice to inference.

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